Daily Papers

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effectiveness of individual components unclear. To enable component-level comparisons, we study this question with a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management. Across four models evaluated on SWE-Bench Verified and Terminal-Bench 2.1, we evaluate 176 matched settings spanning five context-management strategies, four context-window budgets, and targeted ablations of planning and action space. We find that: (1) Context management becomes increasingly valuable as the context-window budget tightens, with most of its benefit coming from preventing context-overflow failures. (2) Staging rule-based elision before LLM-based summarization provides the strongest overall efficiency among the context-management strategies, whereas making elided content recoverable adds machinery that models rarely use and yields no accuracy gain. (3) Planning shifts from an accuracy scaffold for weaker models to a cost saver for stronger models, with little change in accuracy. (4) Predefined tools improve performance for models with weaker bash proficiency, whereas bash-capable models can operate effectively with a bash-only interface and achieve substantially lower cost, especially on command-line-centric tasks. Trajectory-level analysis explains these effects: context management extends execution trajectories without substantially altering agent behavior, planning changes where trajectories stop, and the action space changes the granularity at which code is written. These findings inform model- and budget-aware harness design and provide a modular framework for evaluating future harness components.

Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-observability decision-making. We first report our Gemini Plays Pokemon (GPP) experiments. With iterative human-in-the-loop harness refinement, GPP became the first AI system to complete Pokemon Blue, Yellow Legacy on hard mode, and Crystal without a lost battle. In the hardest stages, the agent itself began iterating on its strategy through long-context memory, surfacing emergent self-improvement signals alongside human-in-the-loop refinement. Continual Harness removes the human fully from this loop: a reset-free self-improving harness for embodied agents that formalizes and automates what we observed. Starting from only a minimal environment interface, the agent alternates between acting and refining its own prompt, sub-agents, skills, and memory, drawing on any past trajectory data. Prompt-optimization methods require episode resets; Continual Harness adapts online within a single run. On Pokemon Red and Emerald across frontier models, Continual Harness starting from scratch substantially reduces button-press cost relative to the minimalist baseline and recovers a majority of the gap to a hand-engineered expert harness, with capability-dependent gains, despite starting from the same raw interface with no curated knowledge, no hand-crafted tools, and no domain scaffolding. We then close the loop with the model itself: an online process-reward co-learning loop, in which an open-source agent's rollouts through the refining harness are relabeled by a frontier teacher and used to update the model, drives sustained in-game milestone progress on Pokemon Red without resetting the environment between training iterations.

Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks. Existing benchmarks evaluate these agents almost exclusively on outcome correctness: whether generated code passes tests or resolves issues. We argue that this outcome-only lens is insufficient: an agent that arrives at a correct solution through reckless trial-and-error, without planning, verification, or graceful recovery, is fundamentally less reliable than one that follows sound engineering discipline. We introduce RigorBench, the first benchmark designed to measure process discipline in AI coding agents. RigorBench evaluates these harnesses across five pillars: Planning Fidelity, Verification Coverage, Recovery Efficiency, Abstention Quality, and Atomic Transition Integrity. A composite RigorScore aggregates these dimensions into a single metric via a weighted sum. We curate a suite of 30 tasks spanning five categories - Plan-Then-Build, Verify-Or-Die, Doom Loop Gauntlet, Know When to Fold, and Don't Break the Build-and evaluate leading harnesses in a controlled with/without experimental design against baseline coding assistants. Our results show that structured process discipline not only improves process quality scores by an average of 41% but also raises downstream outcome correctness by 17%, providing the first quantitative evidence that how agents code matters as much as what they produce. We release the full benchmark, scoring rubrics, and trajectory analysis tools as open-source artifacts.

As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them. This makes automated harness optimization -- the iterative and evaluation-guided improvement of a harness by an AI system -- both an important route to improving AI systems and a demanding capability for AI systems themselves. Yet the community lacks a common protocol for measuring how well frontier LLMs perform at this task. We introduce HarnessOpt-Bench, a benchmark for end-to-end harness optimization under expensive and stochastic evaluation. An optimizer, an LLM paired with a coding harness, receives a target agent's seed harness, graded evaluation feedback, and a fixed target-evaluation budget. It edits the harness and nominates a final candidate, which is scored by its normalized gain over the seed on a held-out test partition that remains inaccessible throughout search. A trusted execution environment enforces the evaluation boundary, meters target-agent resource use, and preserves candidate versions for audit. We evaluate 5 frontier LLMs as optimizers both under a shared coding harness and under their native harnesses across 4 downstream tasks, over 111 scored runs. Experiment results show that optimizer models separate more than the coding harnesses they act through, native harnesses are not consistently superior, and gains vary substantially across tasks and seed regimes. These results establish harness optimization as a measurable and discriminative capability with large space for improvement.

Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains difficult and often loses important training signals. We bridge this gap with polar, a rollout framework for scalable asynchronous RL over arbitrary agent harnesses. Polar treats the agent harness as a black box: it proxies LLM API calls, records token-level model interactions, and reconstructs token-faithful trajectories for training. Each rollout node efficiently manages runtime prewarming, agent execution, trajectory reconstruction, and evaluation in parallel, exposing asynchronous service endpoints that can be consumed by independent trainers at scale. This decoupled design makes Polar agnostic to agent harnesses, training infrastructure, and RL algorithms while improving compute utilization for long-running agent workloads. We validate polar by training agents on software-engineering tasks with popular coding harnesses. Using simple GRPO, polar improves Qwen3.5-4B by 22.6, 4.8, 0.6 and 6.2 points on SWE-Bench Verified with the Codex, Claude Code, Qwen Code and Pi harnesses, respectively. We further demonstrate Polar for offline data generation over custom harnesses and ablate trajectory reconstruction strategies. Polar rewrites its preceding work, Prorl Agent, and has been registered as one of NeMo Gym environments.

For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot programming with the open-world adaptability of model-free policies? We focus on "Variational Automation" (VA), a class of tasks that have larger variations in object geometry and pose than fixed automation. Model-free policies often struggle to close the reliability gap for VA tasks, which must be executed persistently and reliably in commercial and industrial applications. Motivated by prior work on Task and Motion Planning (TAMP) and the Robot Operating System (ROS), we introduce Graph-as-Policy (GaP), a multi-agent coding harness that generates directed computation graphs with perception, planning, and control nodes from a Modular Open Robot Skill Library (MORSL). GaP then generates an internal simulation environment to rehearse task instances with different graphs in parallel to iteratively refine the graph structure and parameters to improve success rates and throughput. Evaluation with 8 new open VA task benchmarks, 4 in-simulation and 4 in real-world, suggests that GaP can achieve success rates that significantly outperform baselines. Details, code, and data can be found online: https://graph-robots.github.io/gap

Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language. However, this free-form communication can rapidly inflate token usage, consume the shared context window, and ultimately affect both system performance and inference cost. We analyze five common inter-agent communication strategies across two MAS topologies, finding that no fixed strategy is universally optimal. Instead, effective inter-agent messages consistently preserve action-centered information needed by downstream agents. Building on this, we propose the PACT (Protocolized Action-state Communication and Transmission), which treats inter-agent communication as a public state-update problem and projects each raw agent output into a compact action-state record before it enters shared history. Across different MAS topologies, PACT consistently improves the performance-cost trade-off, achieving comparable or stronger task performance with substantially fewer tokens. The gains extend to production coding harnesses: PACT lifts OpenHands' resolve rate at -10% tokens-per-resolved, and is resolve-neutral on SWE-agent while halving input tokens. Our code is publicly available at https://github.com/iNLP-Lab/PACT.

AI co-scientists could accelerate computational research, but over a long-running study the workflow also has to stay inspectable, resumable and reproducible, which requires persistent computational state and provenance. Here we present OpenAI4S, an open-source scientific research agent built around the principle of Code as Action, Science as Sessions. OpenAI4S combines a persistent computing runtime with research-session management: orchestration is handled through structured tool calls, while scientific actions are represented as complete code cells executed in persistent Python and R kernels. An append-only Action Ledger, per-cell execution records, versioned artifacts, environment records, and workspace checkpoints preserve how results were produced and support session recovery, branching, and extension. Configurable sandboxing, permission controls, and code and trajectory screening provide complementary safeguards. We evaluate OpenAI4S on 36 research scenarios spanning retrosynthesis, molecular dynamics, protein binder design, protein mutation, catalyst screening, and mineral spectroscopy, measuring scientific task accuracy, workflow completeness, and reproducibility of the resulting repositories. OpenAI4S achieves an overall score of 7.83, compared with 5.7--6.4 for a general-purpose coding harness evaluated with three frontier models, with the largest gains on long-horizon and computation-intensive workflows. These results suggest that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows. Environment specification and full rerunnability remain weak for every evaluated system, ours included, so reproducibility is still an open problem for scientific agents. The system is available under the MIT license at https://github.com/PKU-YuanGroup/OpenAI4S{github.com/PKU-YuanGroup/OpenAI4S}.

We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality datasets of executable 3D code, a coding harness for spatial reasoning and automated verification, and practical guidance for 3D coding. First, we construct 3DCodeVerse-2M, a large-scale curated dataset of standalone 3D executable code. We build this corpus by collecting open-source data, converting specialized representations, and generating new programs with coding agents. Each program is packaged with the source files and associated assets required for execution in its declared environment, along with available descriptions and verification records. Second, we develop the 3DCodeVerse Harness, a multi-agent directed acyclic graph framework for generating and refining 3D content. It uses execution checks, spatial measurements, and visual feedback to automatically evaluate and revise generated programs without human feedback during generation. Third, we conduct systematic empirical studies of 3D coding, establishing baselines with fine-tuned open models and deriving practical guidance through component-level analyses of our harness. Extensive experiments demonstrate that fine-tuning on our dataset significantly improves the 3D coding capabilities of open-source models. Notably, our 3DCodeVerse harness achieves a 90% win rate against Claude Design (3D Object) in pairwise human evaluations, when both are utilized by Claude Opus 5.5.

Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across editable components, voluminous trajectories that bury actionable signal, and edits whose effect is hard to attribute. We introduce Agentic Harness Engineering (AHE), a closed loop that addresses these challenges through three matched observability pillars: (1) component observability gives every editable harness component a file-level representation so the action space is explicit and revertible; (2) experience observability distills millions of raw trajectory tokens into a layered, drill-down evidence corpus that an evolving agent can actually consume; and (3) decision observability pairs every edit with a self-declared prediction, later verified against the next round's task-level outcomes. Together, these pillars turn every edit into a falsifiable contract, so harness evolution proceeds autonomously without collapsing into trial-and-error. Empirically, ten AHE iterations lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI (71.9%) and the self-evolving baselines ACE and TF-GRPO. The frozen harness transfers without re-evolution: on SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains across three alternate model families, indicating the evolved components encode general engineering experience rather than benchmark-specific tuning. Ablations localize the gain to tools, middleware, and long-term memory rather than the system prompt, suggesting factual harness structure transfers while prose-level strategy does not.

Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execution feedback. However, the native execution environments of these harnesses are inherently misaligned with policy-gradient training: environmental crashes and reward hacking corrupt outcome signals, while train-inference discrepancies decouple rollout behavior from policy updates. To address this, we present LEGO-RL, a framework that bridges native coding-agent harnesses with scalable policy-gradient optimization without modifying their internal control flow. LEGO-RL is built upon three pillars: (1) faithful optimization via in-process LLM proxying that captures raw generation streams for token-level alignment and robust trainer-side log-probability recomputation, even under harness-side compaction or re-serialization; (2) reliable execution via scalable sandbox orchestration featuring image caching and stage-wise defenses to mitigate reward hacking; and (3) observable training through an integrated plugin that automates validation and monitoring, paired with a Live UI for granular trajectory diagnostics. We evaluate LEGO-RL by training the sparse MoE model Qwen3.5-35B-A3B with GSPO across three native coding-agent harnesses. LEGO-RL improves Qwen3.5-35B-A3B across OpenHands SDK (64.0% to 70.4%), Claude Code (62.4% to 68.2%), and OpenCode (57.2% to 66.6%) on SWE-bench Verified, while maintaining a rollout-training probability correlation above 0.99.

Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools, manages context, and decides when to stop) is often under-specified. Model-to-model comparison is valid when the harness is fixed; when it varies, performance and efficiency conflate model and scaffold effects. We evaluate Qwen 3.6 Plus and MiniMax M2.5 across three open-source harnesses (Goose, OpenCode, OpenHands-SDK) on a stratified 50-task subset of Terminal-Bench Pro. Harness choice induces up to a 40x difference in tokens per solved task, while paired within-model pass-rate differences remain 0-8 percentage points (95% paired-task bootstrap CIs include zero except for the largest gap). Failure fingerprints replicate across models (REASON for Goose, VERIFY/MAX_TURNS for OpenHands-SDK, idle-loop/TIME for OpenCode), indicating harness-level biases that are largely model-independent. For human-centered coding-agent evaluation, model name alone is an incomplete comparison unit: harness-model pairs determine real-world cost, latency, and oversight burden; no-action turns are a per-task wait tax, not just a token tax. We therefore recommend selecting harness-model pairs by pass rate under token/latency budgets, and reporting token usage, latency, and full harness specifications alongside any model comparison. We release anonymized configs, raw trial logs, aggregated snapshots, and analysis scripts.

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

Coding agents now interleave LLMs with retrieval over the working repository, and retrieval implementations vary widely across deployed harnesses. Inside a fixed coding-agent harness on a fixed model, does adding a structural codebase index actually change cost or resolve? We ran three arms (the harness with the index, the same harness without it, and an agentic-grep comparator) on SWE-PolyBench Verified and SWE-bench Pro with Claude Opus 4.7 held fixed throughout, across three seeds, inside a leak-audited per-task sandbox. The within-harness ablation produces a large localization gain and a statistically separated resolve gain, with no cost penalty per cell and lower cost per solve. The cross-harness check shows that the index does not regress against an agentic-grep baseline on resolve or localization, again at no cost penalty. We release the per-cell exclusion ledger, the leak-audit script, the localization extractor, and the results database. The deployment question for a structural codebase index is thus not whether it is too expensive to run (across seeds, the index lands at a lower $/solved than agentic grep) but whether the workload includes multi-file changes where structural ranking pays off.

AI coding agents set up projects by reading documentation and installing the dependencies it lists, without verifying their names, sources, or known vulnerabilities. By editing only a README, requirements file, or Makefile, an attacker can redirect the agent to an untrusted registry, a known-vulnerable version, or a wrong-but-plausible name: documentation becomes a vector for code execution. We present the first systematic evaluation of package-install-time supply-chain attacks delivered through ordinary project-setup documentation across production coding-agent harnesses, probing frontier models on twelve scenarios in five attack classes, grounded in documented incidents. The same model catches an attack through one harness and installs it through another: install-time security rests on the harness-model combination, not the model alone. Agents catch blatant typosquats reliably, but plausible separator-confusion names (azurecore for azure-core) slip through, and how often depends on the harness-model pairing. Source-based attacks like registry redirection are missed almost everywhere. The source blind spot recurs on npm and Cargo, where nearly every model installs the untrusted dependency; name detection carries over less consistently across ecosystems. Security-oriented prompts recover part of the gap but only for the dimension they name; a deterministic pre-install check that verifies names, sources, and versions before any code runs closes most of it.

Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides. These are different claims. We test each one. mimeo is an open-source tool that finds a person's public work, checks each extracted quotation against the cached source text, and writes a file an agent can load. Eight logged builds averaged 38 model calls; the check rejects 13.2% of extracted quotations. We tested four expert files with one coding-agent harness. Knowledge access was clearest: mimeo answered all 20 obscure, quotation-heavy questions; no closed-book condition answered more than 10. Keyword search (BM25) over the same pages answered 15-17, a gap this sample cannot resolve. Grounding showed one clear benefit: personas written from model memory misstated a documented position on 1-4 of 20 answers under every grader; the plain agent and mimeo never did. Every persona was easy to spot on short open prompts, and adding task material lowered identification by 18-23 points. mimeo was no more identifiable than a from-memory profile. Judgment transfer remained unresolved because both tests hit their ceiling: every condition found 94-97% of the problems planted in engineering tasks and scored 94-100% on 16 new application scenarios. An AI-judged "sounds like the expert" score changed with the judge: two of four preferred answers based on a model's stereotype, while two found no difference on the same text. That is a caution against relying on a single AI judge. The evidence supports mimeo as a compact, inspectable reference on a person, not as a demonstrated transfer of their judgment. Toolkit and expert profiles: https://github.com/K-Dense-AI/mimeo

AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we introduce Timeline-Bench, a benchmark of 56 real video-editing tasks, each asking an agent to turn raw production material into a finished video. Tasks range from selecting dialog takes and shaping interview footage into a story to cutting commercials from product shots, voiceovers and graphics. Every task provides a brief, source assets, a container and a set of tests. A task is resolved when the output passes every test. The tests check the delivery format, the content and the brief's explicit requirements, and include a quality test calibrated on 2,582 blind judgments by 43 video editors. We evaluate 16 agents that pair frontier models with coding-agent harnesses such as Codex, Claude Code and OpenCode. The best, GPT-6 Astra in Codex with curated editorial guidance, resolves only 15 of the 56 tasks (26.8%), and the average agent resolves 14.0%. Human editors prefer the reference edit in 83.5% of judgments. Most unresolved runs (562 of 771) fail only the quality test: agents perceive footage through stills and transcripts and check their renders for defects, not craft. We release the tasks, verifier and per-run results at https://timelinebench.tensortest.com.

Autonomous embodied agents must sustain a long decision-making loop that involves perceiving, acting, verifying, and self-correcting over many steps. Current systems sustain this loop through task-specific workflows or embodied policies. However, these fixed workflows and policies offer limited flexibility across environments and often lack effective recovery strategies when execution goes wrong. We find that a general-purpose agent can instead sustain the loop on its own. We term this organization agentic embodied control: the reasoning model directly steers every action, keeping reasoning and control aligned. Using zero-shot navigation as a controlled testbed, we equip three coding-agent harnesses with only a monocular RGB camera and discrete actions. At default effort, replicated opus-5 runs average 70.7pm3.5% success, while fable-5 reaches 78% at maximum effort. When a trained waypoint tool is offered alongside primitives, the hybrid fable-5 agent reaches 76.7pm0.6% at default effort, using half the environment steps and under a quarter of the wall time. Across the ablations, model choice dominates performance variation. Observed harness differences are modest, and forced waypoints help weaker models but can hinder stronger ones. Although longer horizons, latency, and context growth remain barriers to sustained autonomy, these results show that a general-purpose model can already achieve competitive embodied control without a navigation policy.

Understanding large codebases is a long-horizon task for Large Language Model (LLM) agents: answering a single question can require building and running the software, tracing execution across files, and synthesizing evidence over tens of minutes. On SWE-Atlas QnA, a benchmark of long-horizon questions over production repositories, a single Claude Code agent (Opus 4.6) resolves only 32.3% of tasks. Dividing the work among agents with clean contexts mitigates this limitation. However, the subtasks of code comprehension are interdependent. One agent's findings can rewrite another's task, so agents must coordinate during execution, not only at phase boundaries. Existing multi-agent systems support such exchange only between phases, through staged handoffs or synchronized rounds. Communication and work remain mutually exclusive. A discovery made mid-execution cannot be shared until the next boundary. We present AgentRadio, an asynchronous message-passing layer that equips coding-agent harnesses with three primitives: threads, messages, and waiting for mentions. The last runs as a background task, surfacing teammates' messages without interrupting foreground work, so each agent remains passively aware of its peers and folds new findings into its ongoing task. Under a five-phase protocol of division of labor and negotiation, four agents organized by AgentRadio resolve 62.1% of tasks, 29.8 points above a single agent and above Claude Code with the newer Opus 4.8 (57.2%). Rubric-level analysis shows the gain growing with task difficulty, consistent with mid-course correction as the underlying mechanism. Our code is available at https://github.com/Coral-Protocol/AgentRadio.

A coding agent combines a model with a harness, which decides what the model sees, which tools it can use, and how the work continues. We ask whether changing the harness changes the result when the model and task stay fixed. We compare two configurations of the same harness on three coding benchmarks. The control supplies the full conversation in time order, while the treatment keeps the same record but mechanically shortens older tool results as the context fills and responds to repeated or stalled work. Under tight context, the treatment raises mean per-task fail-to-pass fraction (F2PF) in all three pressure comparisons and increases complete solutions on SWE-bench Verified and SWE-bench Pro. The tight-window Verified comparison uses 169 tasks, a 20,480-token window, and a fixed 480-second attempt endpoint; on this cohort, treatment raises mean per-task F2PF from 28 percent to 49 percent and complete solutions from 43 to 72. Without model-specific retuning, the same frozen treatment also raises both endpoints on the same cohort for three additional models with different designs. In the wide-window Qwen3.6 comparisons, observed arm outcomes are close on Verified and Pro, while FeatureBench retains a higher mean per-task F2PF under treatment. On the wide-window Verified cohort, treatment also serves fewer prompt tokens per turn. Because changing the harness changed what unchanged model weights could accomplish, coding-agent evaluations should treat the model and harness together as the tested solver.

General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issue-resolution instances across 8 languages and 43 repositories, drawn from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup. We also release Claw-SWE-Bench Lite for faster validation, which is an 80-instance subset selected by a cost-aware, rank-aware procedure over 17 calibration columns. On the full benchmark, OpenClaw with a minimal direct-diff adapter scores only 19.1% Pass@1, whereas the full adapter reaches 73.4% with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw-style harnesses to perform coding tasks effectively. Across an OpenClaw times nine-model sweep and a five-claw times two-model sweep, model choice changes Pass@1 by 29.4 pp and harness choice by 27.4 pp under fixed models; systems with similar accuracy can differ substantially in total API cost. Claw-SWE-Bench therefore treats harness and cost accounting as first-class axes of SWE-style coding-agent evaluation, providing both a full benchmark and a low-cost reference set for reproducible comparison. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.

LLM-based program evolution relies on evaluation feedback to guide the iterative search for high-performing programs. However, evaluation is often computationally expensive, making it essential to allocate limited resources to candidates that can most effectively advance the search. Existing LLM-based methods typically rely on fixed allocation strategies throughout the search, potentially wasting resources on low-value candidates while overlooking promising ones. We propose EvoAlloc, a self-evolving resource-allocation agent that learns from search experience to revise its strategy for allocating computational resources across candidates. EvoAlloc periodically consolidates prior search and allocation outcomes into reusable experience, which informs subsequent strategy revisions. It further uses a counterfactual exploration mechanism to occasionally evaluate candidates denied resources by the allocator, revealing their outcomes to enrich its experience for future strategy updates. Across coding and agent-harness optimization benchmarks, EvoAlloc requires 59-82% fewer full evaluations and 61-89% fewer total LLM tokens to reach baseline-level performance. Moreover, under the same full-evaluation budget, EvoAlloc achieves 8.7-12.0% higher final performance.

Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing benchmarks often center on localized tasks or end-state outcomes, offering limited insight into sustained execution. We introduce LOOPSBENCH, a long-horizon benchmark for loop engineering in coding agent evaluation. Each task is a dependency DAG over separately testable development units with source-evidenced prerequisite edges. LOOPSBENCH comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains. Its flow-aware runtime releases tests along the ready frontier and retains completed nodes as regression obligations. We evaluate frontier coding agents paired with widely used loop implementations. The strongest configuration, Opus-4.7 with Claude Code and outer continuation, resolves 25.00% of tasks. Recorded plans recover only part of the source-recovered prerequisite DAG, and regression events remain visible across the evaluated loop profiles. We open source the benchmark data and code, including all tasks, more than 5,300 development units, and executable tests, at microsoft/Loopsbench.

Large Language Models (LLMs) have shown strong performance in solving mathematical problems, with code-based solutions proving particularly effective. However, the best practice to leverage coding instruction data to enhance mathematical reasoning remains underexplored. This study investigates three key questions: (1) How do different coding styles of mathematical code-based rationales impact LLMs' learning performance? (2) Can general-domain coding instructions improve performance? (3) How does integrating textual rationales with code-based ones during training enhance mathematical reasoning abilities? Our findings reveal that code-based rationales with concise comments, descriptive naming, and hardcoded solutions are beneficial, while improvements from general-domain coding instructions and textual rationales are relatively minor. Based on these insights, we propose CoinMath, a learning strategy designed to enhance mathematical reasoning by diversifying the coding styles of code-based rationales. CoinMath generates a variety of code-based rationales incorporating concise comments, descriptive naming conventions, and hardcoded solutions. Experimental results demonstrate that CoinMath significantly outperforms its baseline model, MAmmoTH, one of the SOTA math LLMs.

The study on GitHub Copilot by GovTech Singapore's Engineering Productivity Programme (EPP) reveals significant potential for AI Code Assistant tools to boost developer productivity and improve application quality in the public sector. Highlighting the substantial benefits for the public sector, the study observed an increased productivity (coding / tasks speed increased by 21-28%), which translates into accelerated development, and quicker go-to-market, with a notable consensus (95%) that the tool increases developer satisfaction. Particularly, junior developers experienced considerable efficiency gains and reduced coding times, illustrating Copilot's capability to enhance job satisfaction by easing routine tasks. This advancement allows for a sharper focus on complex projects, faster learning, and improved code quality. Recognising the strategic importance of these tools, the study recommends the development of an AI Framework to maximise such benefits while cautioning against potential over-reliance without solid foundational programming skills. It also advises public sector developers to classify their code as "Open" to use Gen-AI Coding Assistant tools on the Cloud like GitHub Copilot and to consider self-hosted tools like Codeium or Code Llama for confidential code to leverage technology efficiently within the public sector framework. With up to 8,000 developers, comprising both public officers and vendors developing applications for the public sector and its customers, there is significant potential to enhance productivity.

Long-horizon coding agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated agents, and multi-agent coordination. These trends pose two complementary challenges for the agent harness. First, developers need to compose capabilities, reconfigure execution logic, and scale increasingly complex agent systems without repeatedly rebuilding orchestration. Second, complex coding tasks continuously produce new evidence---such as semantic diagnostics, execution outcomes, task progress, and changing context relevance---that should dynamically influence subsequent runtime decisions. We characterize these challenges as Structural Composability and Runtime Adaptivity. We present openJiuwen, an open-source harness designed for both developer composability and adaptive task execution. openJiuwen provides a shared execution substrate and Rail-based capability composition across single agents, delegated sub-agents, and Swarm Flow, enabling developers to construct sophisticated agent harnesses under common execution semantics. It further adapts framework-controlled runtime decisions around a fixed model policy, allowing evolving evidence to dynamically affect context, feedback, and task control toward successful completion. We systematically evaluate openJiuwen on SWE-bench Verified and Terminal-Bench 2.1, where it achieves 82.6% and 87.19%, respectively, exceeding the strongest selected official-leaderboard point estimates by 3.4 and 3.39 percentage points. These results show that openJiuwen achieves strong performance on complex coding tasks while providing a composable and adaptive harness design.

Coding agents ship with one kind of memory: documents. Instruction files, plan artifacts, and auto-written memory directories are deliberately authored and deliberately retrieved: the agent must choose to write them and choose to read them back. Human expertise runs on a second tier that never gets written down: situationally-bound operational facts (gotchas, locations, local conventions) encoded as a side effect of the work and retrieved involuntarily when the situation cues them. We argue this second tier is the load-bearing one for long-running agents and must be a harness property, not an agent choice. We contribute: (1) a two-tier design theory grounded in the cognitive literature on memory offloading, incidental encoding, and event-based prospective memory, each mapped to an architectural requirement; (2) a cue-anchored memory model where memories carry first-class trigger conditions over a composable vocabulary (path, symbol, semantic, event, temporal), evaluated deterministically by the harness, a composition no surveyed academic or shipped system provides; (3) a controlled evaluation on a real coding task showing that voluntary memory use is near zero even with a pre-seeded store (0 memory operations in 114 turns), that deterministic injection delivered in every seeded run with zero false alarms, and that 39% of intra-session re-reads re-buy content paid for before a compaction boundary; (4) a repeated-compaction decay probe: ten facts held only in conversation vanish at the first summary and stay absent from 106 of 108 compactions, and the deprived agent greps the harness's own session files to rebuild them, while the same facts injected from a harness-owned store arrive intact through all 138 compact-resumes as the final summary carries none. Delivery, not storage, is the product: the reliable memory channel for agents is the one the agent never has to think about.

The landscape of AI coding assistance is undergoing a fundamental shift from complex IDE plugins to versatile, terminal-native agents. Operating directly where developers manage source control, execute builds, and deploy environments, CLI-based agents offer unprecedented autonomy for long-horizon development tasks. In this paper, we present OPENDEV, an open-source, command-line coding agent engineered specifically for this new paradigm. Effective autonomous assistance requires strict safety controls and highly efficient context management to prevent context bloat and reasoning degradation. OPENDEV overcomes these challenges through a compound AI system architecture with workload-specialized model routing, a dual-agent architecture separating planning from execution, lazy tool discovery, and adaptive context compaction that progressively reduces older observations. Furthermore, it employs an automated memory system to accumulate project-specific knowledge across sessions and counteracts instruction fade-out through event-driven system reminders. By enforcing explicit reasoning phases and prioritizing context efficiency, OPENDEV provides a secure, extensible foundation for terminal-first AI assistance, offering a blueprint for robust autonomous software engineering.

Agents driven by large language models are increasingly deployed on long-horizon tasks, where they use tools and modify real workspaces. How well they perform depends as much on the harness around the model as on the model itself. Existing benchmarks measure downstream task success under a fixed harness, leaving harness engineering itself unexplored. We propose Doc2Harness, a two-stage benchmark that evaluates long-horizon harness engineering directly. In Stage 1, a build model operating inside a fixed builder harness receives an interface-only contract skeleton and a development document that consolidates behavior across twelve frontier harnesses, and then constructs a complete candidate harness in an isolated container. In Stage 2, the frozen candidate harness runs in containers separate from the construction environment, one per test case, and is driven end to end by a scripted mock model. We score each test case using four observable channels, namely the requests sent to the model, the files on disk, the process exit code, and the command output; positive controls rule out vacuous passes. Across nineteen frontier models, each evaluated with three independent builds on 328 test cases, GPT-6 Astra achieves the highest pass rate at 53.05%, while the weakest model reaches 27.44%, a gap of roughly twenty-six percentage points. Even the strongest model fails nearly half of the test cases, and failures cluster around how cross-cutting functionality is split across modules. To our knowledge, Doc2Harness provides the first deterministic benchmark for measuring long-horizon harness engineering.

The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering.

Agent performance increasingly depends on harness engineering, yet harness design is usually buried in controller code and runtime-specific conventions, making it hard to transfer, compare, and study as a scientific object. We ask whether the high-level control logic of an agent harness can instead be externalized as a portable executable artifact. We introduce Natural-Language Agent Harnesses (NLAHs), which express harness behavior in editable natural language, and Intelligent Harness Runtime (IHR), a shared runtime that executes these harnesses through explicit contracts, durable artifacts, and lightweight adapters. Across coding and computer-use benchmarks, we conduct controlled evaluations of operational viability, module ablation, and code-to-text harness migration.

Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end Vision-Language-Action (VLA) models provide strong local visuomotor skills, but they are trained on in-distribution task trajectories and often fail under deployment perturbations such as semantic retargeting, goal re-binding, spatial-layout shifts, and unstable local contacts. LLM coding agents provide complementary semantic and compositional reasoning, but purely analytic primitives struggle with irregular grasping, constrained placement, and articulated-object interaction. We present Harness VLA, a memory-augmented agentic framework that exposes a frozen VLA as a retryable contact-rich primitive and composes it with a small fixed library of analytic primitives for grounding, staging, transport, navigation, and release. Rather than expanding the skill library, the harness learns the operating range of these fixed primitives from task-specific execution traces, global success rules, and failure models. By lifting semantic re-grounding, non-contact execution, and VLA re-staging to the planner while reserving the frozen VLA for local contact-rich phases, Harness VLA extends pretrained VLAs beyond their original trajectory distribution without finetuning. Across perturbed tabletop, household kitchen, and clean-to-randomized bimanual manipulation, Harness VLA improves over the strongest relevant baselines by 38.6 and 25.4 percentage points on LIBERO-Pro and RoboCasa365, respectively, and reaches 58.4% on RoboTwin C2R.

Recent autonomous penetration testing papers report high benchmark scores while adding multi-component security harnesses around frontier LLMs. Because these systems often change both architecture and backbone model, it is difficult to tell how much performance comes from the harness rather than from the underlying model. This paper presents a controlled study on the 104-task XBOW benchmark using default coding CLI agents as plain-agent baselines. We first run Codex, OpenCode, and Pi with the same GPT-5 model, budget, target interface, and scoring rule. This phase identifies the strongest same-model baseline and tests whether security-specific prompt variants improve its observed score. We then compare the default Codex scaffold with published MAPTA and PentestGPT V2 results under the closest available model matches. Finally, we repeat the plain-agent experiment with GPT-5.2 and GPT-5.5 to measure model scaling inside the same scaffold. The results show a mixed but practical picture. Specialised harnesses can add measurable benchmark lift and may improve cost efficiency, but plain coding agents already solve a large share of the benchmark; repeated plain-agent runs can match or exceed some published architecture scores in union coverage, and newer models substantially improve the same scaffold. Future evaluations should report model-matched plain-agent baselines before attributing benchmark gains to architecture design alone.

Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their critical role in machine learning infrastructure, their operational challenges and engineering concerns have received limited attention so far. We present an empirical study of 57 evaluation harnesses, deriving a five-stage harness model and classifying 16,560 issues by workflow stage and root cause. Most harness operational challenges concentrate in the Specification stage (41.4% of issues), where harnesses integrate external models, datasets, and scoring judges. The three most frequent root causes of operational challenges are unimplemented features (24.3%), documentation gaps (20.3%), and missing input validation (17.2%), which together account for 61.7% of classified issues, spanning both defects in existing functionality and capability gaps that block intended workflows. Root causes also vary by workflow stage: environment incompatibility and external dependency breakage account for 36.2% of provisioning issues, whereas algorithmic error (25.9%) and validation gap (22.5%) dominate assessment issues. Together, these contributions establish an empirical foundation for treating evaluation engineering as a distinct software engineering concern.

3D content inherently encompasses multi-modal characteristics and can be projected into different modalities (e.g., RGB images, RGBD, and point clouds). Each modality exhibits distinct advantages in 3D asset modeling: RGB images contain vivid 3D textures, whereas point clouds define fine-grained 3D geometries. However, most existing 3D-native generative architectures either operate predominantly within single-modality paradigms-thus overlooking the complementary benefits of multi-modality data-or restrict themselves to 3D structures, thereby limiting the scope of available training datasets. To holistically harness multi-modalities for 3D modeling, we present TriMM, the first feed-forward 3D-native generative model that learns from basic multi-modalities (e.g., RGB, RGBD, and point cloud). Specifically, 1) TriMM first introduces collaborative multi-modal coding, which integrates modality-specific features while preserving their unique representational strengths. 2) Furthermore, auxiliary 2D and 3D supervision are introduced to raise the robustness and performance of multi-modal coding. 3) Based on the embedded multi-modal code, TriMM employs a triplane latent diffusion model to generate 3D assets of superior quality, enhancing both the texture and the geometric detail. Extensive experiments on multiple well-known datasets demonstrate that TriMM, by effectively leveraging multi-modality, achieves competitive performance with models trained on large-scale datasets, despite utilizing a small amount of training data. Furthermore, we conduct additional experiments on recent RGB-D datasets, verifying the feasibility of incorporating other multi-modal datasets into 3D generation.

Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters. We run the missing crossed comparison: an integrity-clean three-arm ablation (baseline / bash_only / code_only) on synthetic computation tasks and SWE-bench Mini modification tasks, holding model, harness, and prompts fixed, with two agents (Claude Code, OpenAI Codex CLI) so the comparison spans both regime and agent-design axes. Across the four resulting (regime, agent) cells, restricting the agent to a single execute_code MCP tool is cheaper than -- or statistically tied with -- its cheapest tool-rich rival in three cells (significantly on Artifact/Claude and SWE-bench/Codex; directionally on Artifact/Codex), with pass rates statistically tied within each cell. The lone exception is SWE-bench/Claude, where code_only is directionally costlier (+14.4%, not significant); a conditional-cost analysis localizes that gap to failure-cost on doomed-run trajectories, not a per-edit tax on successful runs. Two implications: the cheapest tool surface is jointly determined by task regime and agent design rather than by either axis alone, and the headline cost signal lives in cache-adjusted cost -- not pass rate, which is invariant across surfaces at the model sizes we evaluate. The benchmark harness, task suite, and analysis code are available at https://github.com/hyang0129/onlycodes.

The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure around it. We ask whether the same paradigm extends to embodied agents in the physical world. We present Thea, a harness in which an agentic loop orchestrates robot capabilities, each wrapped as a callable tool. It inherits the core components of coding agents, modified as the physical world requires. The world, however, withholds two abilities that software grants for free: reading the state of the world, and judging the outcome of an action. To bridge these gaps, Thea introduces Scene Graph as Context, a persistent, symbolic representation of the world, and Evaluation as Exit Codes, which detects when an action should terminate, judges whether it succeeded, and on failure diagnoses the cause. Together they close the loop between the agent and the physical world. Rich behaviors then emerge from the composition of tools, and the closed loop carries long-horizon tasks to completion in real environments.

Human supervisors rely on coding agents' reports to assess progress, verify repairs, and decide when to intervene. But a supervisor cannot investigate a failure they were never told occurred. Failed attempts, workarounds, and unresolved risks may disappear from routine reports, leaving supervisors unaware of issues that warrant scrutiny. We conduct CTXGAP, a measurement study quantifying the gap in task-state recoverability between agents' accumulated user-facing reports and their full recorded execution contexts. Across 37 coding tasks and 4,799 valid probes, agents answer 93.6% of task-state questions on demand; full-context readers recover 92.7%, while report-only readers recover 52.0%, a 40.7-point gap. At the final checkpoints of 30 verified fixes, the gap remains 34.8 points. Human annotation identifies states mentioned without enough supporting detail as the largest category of unrecovered information, and model-assessed supervision-relevant states retain substantial gaps. Full terminal scrollback improves recovery to 73.6% but still trails full context. Under matched report lengths, context-informed rewrites improve recovery by about eight points, without a detectable targeted-over-natural advantage. Positive gaps persist across harnesses and independent DeepSeek execution and measurement. CTXGAP establishes report-based task-state recoverability as a complementary evaluation dimension.

Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems. However, they tend to converge onto a single high-level approach, then proceed with low-level edits while missing other superior approaches to the problem. We hypothesize two harness-level design choices contribute to this behavior: accumulating context in a single long-running agent and only exposing a single program state to edit. We introduce SwarmResearch, an orchestrator-subagent harness in which a Shepherd Agent uses global context to steer a population of Search Agents, each operating with local context in their respective git branch. On open-ended optimization tasks, SwarmResearch discovers better or comparable solutions to state-of-the-art LLM-guided evolution and multi-agent techniques on 13/15 tasks, driven by higher-level exploration. Compared with fixed scaling of serial and parallel agents, SwarmResearch's orchestrator-guided scaling discovers better-performing solutions by adapting parallelism at different search depths.

We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a single language and depend on manually curated tasks. We introduce Zero2Repo, a benchmark in which an agent receives a product requirements document, an interface contract, and an empty workspace, and must deliver a complete repository in the project's native ecosystem. Tasks are produced by a language-agnostic authoring pipeline that converts real, version-pinned open-source projects into behavioral specifications, reproducible environments, and hidden acceptance tests. Each task is validated by execution: a reference implementation derived from the upstream project must pass, and adversarial validation must show that the tests reject incorrect implementations. Evaluation runs production coding agents in isolated containers, withholds the acceptance tests until an explicit submission, and assigns a binary reward only when every test passes, with no LLM judge. The pipeline and harness make no language-specific assumptions and apply to mainstream programming ecosystems; the current release contains Python, TypeScript, Go, and C++ tasks. Even on 11 tasks drawn from repositories that frontier models have very likely seen during training, the strongest agent solves only 10, and every failing submission passes 90-99% of the hidden tests; for the two strongest agents, 67-100% of failed tests trace to a single omission or a low-frequency rule stated in the specification rather than to a missing subsystem, so each failure is a concrete target for improvement.

Diffusion language models promise bidirectional context and infilling capabilities that autoregressive coders lack, yet practical systems remain heavyweight. We introduce CoDA, a 1.7B-parameter diffusion coder trained on TPU with a fully open-source training pipeline. CoDA pairs large-scale diffusion pre-training with code-centric mid-training and instruction tuning, enabling confidence-guided sampling that keeps inference latency competitive. On Humaneval, MBPP, and EvalPlus, CoDA-1.7B-Instruct matches or surpasses diffusion models up to 7B parameters. Our release includes model checkpoints, evaluation harnesses, and TPU training pipelines to accelerate research on lightweight diffusion-based coding assistants.

Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window. We model this as reconstructing a coupled-fact graph: at each edit, a required fact comes from recent context or parametric memory, and the facts covered by neither form coherence debt. We supply and withhold each channel and inject faults across seven models and five harnesses. As expected, no model completes a task on an unseen API with both channels empty, and putting the facts in the prompt restores success. When a rename defeats what models memorized about a real library, all seven fail in the same place, passing and missing the same tests. Availability decides the outcome and distance does not: withholding a fact costs exactly the work it supports, and a supplied fact works as well far from the edit as next to it. Harnesses pay unequal prices for it: configurations that all pass every test differ more than tenfold in tokens consumed because they rebuild the same content at different rates, and spending more recovers nothing when facts are withheld. A missing fact produces wrong work rather than absent work: an agent asked to act acts, fabricating the file or guessing the value, so instruments built on reads look for a hole already filled. How often it says it is blocked instead is a property of the model, from every trial to none. Availability does not settle every edit: where standard and code disagree, agents follow the standard even when it prescribes the worse code, so a stale convention file costs more than no file. Because parametric memory substitutes for reading, on SWE-bench, where models likely know the repositories, reads no longer predict success. Harnesses should keep the facts an edit depends on available when the agent writes, and check that availability against what the agent produces rather than what it reads.

An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this task. Agent optimization differs fundamentally from conventional software engineering: the target agent interleaves deterministic code with stochastic LLM completions, requiring structured capture of both intermediate reasoning and downstream execution outcomes. To address these challenges, we introduce VERO (Versioning, Rewards, and Observations), which provides (1) a reproducible evaluation harness with versioned agent snapshots, budget-controlled evaluation, and structured execution traces, and (2) a benchmark suite of target agents and tasks with reference evaluation procedures. Using VERO, we conduct an empirical study comparing optimizer configurations across tasks and analyzing which modifications reliably improve target agent performance. We release VERO to support research on agent optimization as a core capability for coding agents.

As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback. Token efficiency therefore becomes important for scaling recursive self-improvement. We take an RSI-inspired approach at the harness layer, scaling auto-research loops across increasingly numerous and diverse environments for harness rollouts. At this scale, the process yields reusable improvements that transfer beyond their development setting, moving automated harness discovery toward production-level outcomes. Four mechanisms survive selection and form SoL-Pi, spanning action execution, context compaction, observation handling, and delegated reading. On the 51-task EdgeBench evaluation, SoL-Pi achieves performance comparable to Pi across GPT-5.6 Sol and Opus 5 while reducing recorded token traffic by 44.7-49.0% and API cost by about one third. In other words, estimated hourly savings are \8.75-13.50 relative to native Codex and Claude Code harnesses, and \4.36-5.71 relative to Pi.

An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically establishing a form of recursive self-improvement (RSI) at the agent-system level. However, such recursive evolution may overfit by memorizing the training tasks, showing large in-distribution gains that shrink or even vanish on out-of-distribution benchmarks. We introduce Regularized Recursive Self-Improvement of Agent Harnesses (RRSI), which incorporates the principles of regularizations into harness self-improvement by constraining the evolution candidate proposal and selection. The proposer operates with a temporally annealed budget, limiting how many edits a candidate can bundle, and it encourages unexplored trajectories based on evolution history. The selector is equipped with a critic and a pruner: the critic screens benchmark-specific proposals, while the pruner, removes changes that are too small, too expensive, or no longer useful. Together these constraints favor reusable agent mechanisms over benchmark-specific ones or even noises. Across eight benchmarks spanning coding, agentic workspace and engineering design tasks, RRSI gains up to 14.1 points on the split it evolves against and up to 4.7 points on the five out-of-distribution benchmarks, while producing a harness that runs on 30% fewer policy tokens than the unregularized evolution. Code is available at https://github.com/google-research/rrsi and project page is https://regularized-rsi.com/.

Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-oriented harness to advance agentic game development from rough game prototypes into entertaining games. Recursive Game Creator organizes recursive development around four components: Designer, Builder, Player, and Reviewer. The Designer translates user instructions and Reviewer's feedback into detailed plans. The Builder turns these plans into candidate games. The coding-native Player creates and executes reusable policies through programmatic interfaces to efficiently collect diverse gameplay trajectories, mitigating evaluation bias caused by slow GUI-based collection. The Reviewer uses carefully designed trajectory-based metrics to induce player preferences, integrating with visual evidence and explicit textual preferences to evaluate games against game-specific criteria. Finally, the Reviewer accepts the better version and provides improvement reviews for the next round, closing the recursive loop. Our method achieves state-of-the-art overall performance of 77.89 on GameCraft-Bench. On GameASG-Bench, it achieves a strict task success rate of 53.2%, a 34.1% improvement over the same-model baseline, and the highest mean runtime-check pass rate at 93.4% among compared methods. A user study shows longer playtime and higher ratings. Code is coming soon.

Building gameplay features in a game engine requires more than code, as code that compiles and runs does not necessarily implement the requested gameplay. We introduce CraftBenchUE, an evaluation harness that runs agents in an isolated Unreal Engine environment, reconstructs their saved submissions in fresh projects, and applies deterministic build, asset, and runtime checks without an LLM judge. Based on the harness, we built a benchmark consisting of 70 tasks spanning C++ source, Blueprint assets, and editor scripting. We evaluate seven models under two editor-tool configurations, with a file-and-shell baseline on C++ tasks. We further pair tasks that specify the same gameplay and use the same runtime tests, but require C++ and Blueprint as the deliverables. Across the 10 paired tasks, C++ completion rates exceed Blueprint by 30.0 and 42.9 percentage points in the two tool configurations. Among on-time Blueprint submissions in this paired set that pass asset checks, 42.2% and 50.0% fail explicit runtime assertions. These submissions satisfy asset requirements but fail the required gameplay tests. We will release the harness, task benchmark, and our trajectory findings with the report.

Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automatically when the agent reads matching files. We call these files the agent's harness. Developers add to it whenever they correct the agent, but one success proves little: the same agent can pass a task once and fail it the next time. We present Cortex, a tool that tests changes to the harness instead of trusting them. It saves fixes from the developer's sessions as replayable tasks, finds the corrections that recur, writes one skill or rule at a time, and keeps it only if repeated runs with and without it show a net gain and no task made noticeably worse. Existing text is tested the same way before it is deleted, and Cortex neither adds nor deletes text the agent never used. We tested Cortex with Claude Haiku 4.5 on a repository built for the purpose, with conventions the model tends to break, one area with nothing to learn, and a script playing the developer. On held-out tasks, the harnesses it built made the agent follow the conventions far more often than no skills or rules did, left the comparison area unchanged, and added no text read on every turn. Rules, which load automatically, did most of the work; skills helped only when offered with the files a task touches, and those offered on every turn were rarely opened. Cortex kept none of the useless or harmful suggestions we planted, but the agent never opened the useless ones or the harmful skills, and it reached no verdict on the harmful rules, so the test shows that Cortex keeps no unused text, not that it detects damage. Under the stronger Claude Sonnet 5 a single run's harness added little, and on a real open-source project, where the agent was rarely corrected, Cortex found nothing to learn. We release the tool, the lab and its data.

Large Language Models (LLMs) have significantly advanced automated code generation, yet they struggle with complex coding tasks requiring multi-step logical reasoning. High-quality reasoning data is crucial for improving LLMs' reasoning capabilities, but such datasets remain scarce. Existing approaches either rely on computationally expensive reinforcement learning (RL) or error-prone reasoning chains synthesized by LLMs, posing challenges in scalability and accuracy. To address this challenge, we propose SVRC (Structured and Validated Reasoning Chains for Code Generation), a novel framework that mines, restructures, and enriches reasoning chains from community-driven discussions on software engineering platforms. SVRC refines unstructured and incomplete discussions of coding problems by aligning them with Software Development Life Cycle (SDLC) principles, ensuring that reasoning chains capture real-world problem-solving strategies and support iterative refinement. To evaluate the effectiveness of SVRC, we introduce CodeThinker, an LLM fine-tuned on 12,444 reasoning-augmented samples generated by SVRC. Experiments on LiveCodeBench show that CodeThinker surpasses its base model by 42.86\% on medium-level code problems in terms of pass@1 and outperforms GPT-4o-mini and GPT-4o by 73.14\% and 115.86\%, respectively. Our ablation study further highlights that each component of SVRC contributes to the reasoning capabilities of CodeThinker.

Coding agents have become a major mode of software engineering, but the benchmarks we use to compare them were designed in a pre-agent era: they collapse model, harness, and environment into a single end-to-end score, typically computed against one reference solution, with no component-level signal for iteration. We argue that current coding benchmarks are misaligned with agentic software engineering. A coding agent in practice is not a model: it is a system harness -- a composite of models, harnesses, contexts, environments, and feedback signals, any one of which can move the benchmark score by margins comparable to those between adjacent model generations. We discuss three symptoms: (i) benchmark scores conflate the model with the rest of the harness; (ii) grading against a single reference solution penalises equally valid alternatives; and (iii) the absence of signal at the level of individual harness components makes the end-to-end system score difficult to iterate on.

Agentic coding tools present new opportunities to transform research workflows. The performance of agent systems built depends on both large language models (LLMs) and the harness around LLMs, which is the orchestration code that determines an agent's behavior. We present ToFu, an agentic harness for researchers that reads your codebase, edits files, runs commands, and integrates with your development tools. ToFu plays a dual role in research. As a research assistant, it supports practical research workflows with superior token efficiency, lower cost, and multilingual capability compared with existing agentic harnesses. Its release under the MIT License further enables local deployment for privacy-sensitive users. As a research object, ToFu provides a white-box agentic harness that allows researchers to inspect, modify, and evaluate its orchestration logic, tool-use behavior, and harness design, while retaining strong benchmark performance and an application-level user experience.

Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model parallelism. Existing serving systems and auto-parallelism compilers commit to limited transformations and fixed workload assumptions, so achieving high performance on a new application requires hand-crafting an efficient implementation. We present FlashRT, an agent harness that guides coding agents to lift simple developer-written reference implementations into optimized multi-GPU deployments that flexibly weigh target metrics like latency and throughput. Using a new chain-of-program paradigm, FlashRT directs a generic coding agent through a multi-pass transformation process where an agent transforms the reference into an intermediate representation (IR) to capture data dependencies and persistent-state scopes, validates this IR via a sequential interpreter, and performs static analyses to identify candidate transformations. Then, the agent iteratively implements, verifies, and benchmarks each candidate under a measurement-gated optimization loop to produce effective deployments that span different hardware budgets. Across various applications, including video world models and multimodal LLMs, FlashRT converts reference implementations into highly efficient deployments, delivering up to ~70x latency reduction and 2.8x throughput improvement on NVIDIA B200 GPUs. On AMD MI355X GPUs, FlashRT matches the peak latency reduction while increasing peak throughput improvement to 3.6x, demonstrating that agent-driven optimization can be more scalable on platforms with less mature expert optimization. In fact, for Qwen3-Omni text-to-audio inference, FlashRT reduces response latency by 65% compared to the expert vLLM-Omni implementation on AMD MI355X.

Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the NL2Pipeline gap. To bridge it, we introduce DataFlow-Harness, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines DataFlow-Skills for procedural guidance, a Model Context Protocol (MCP) layer that exposes the live operator registry and current pipeline state, and DataFlow-WebUI, which synchronizes conversational authoring with a visual DAG editor. On a 12-task data-engineering benchmark, DataFlow-Harness achieves a 93.3\% observed end-to-end pass rate. Relative to Vanilla Claude Code, it reduces measured monetary cost by 72.5\% and generation latency by 49.9\%; its observed pass rate is within 0.9 percentage points of the Context-Aware Claude Code baseline while its cost is 42.8\% lower. Per-task analysis indicates that Skills are most useful when construction depends on implicit procedural knowledge. These results show that live platform grounding can produce persistent, editable workflow artifacts with an observed reliability close to script-generation baselines and with lower measured construction cost and latency.

Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system. This creates a repair-assignment problem: the same visible failure may call for model post-training, harness engineering, environment redesign, or benchmark repair depending on its source. Because agent behavior emerges from interactions among models, harnesses, users, tools, memory, and environments, outcome-level labels are often insufficient for improvement. Most failure taxonomies do little to resolve this problem because they are benchmark-specific and lack a shared structure. We introduce an interaction-centric taxonomy that localizes failures to the interactions in which they originate and identifies the responsible component. It organizes 41 failure modes by assigning each to an edge between two components and a fault side indicating where the repair belongs. This makes the taxonomy actionable: model-side failures identify targets for post-training, harness-side failures point to scaffolding and tool-integration fixes, and environment or grader failures reveal evaluation conditions requiring redesign. The schema applies across agent architectures, from coding assistants to long-horizon personal assistants and multi-agent systems. We ground the taxonomy in worked examples from public benchmarks, model system cards, published reports, and logged agent trajectories, and evaluate its reproducibility using independent reasoning agents as judges. Across four frontier models, the strongest judge reaches Cohen's κ=0.76 against human category labels, suggesting that the categories capture shared structure rather than annotator-specific preferences.

Bug validation asks a coding agent to produce an executable witness for a reported bug. The witness combines a concrete input with a testing harness and exposes faulty behavior during execution. Such evidence makes audit findings actionable, yet benchmark evaluation is difficult when cases reuse public historical bugs and witnesses or require manual construction. We present WitnessGym, an automated framework for constructing bug-validation benchmarks through bug injection. It injects bugs into test-reached paths of real projects, rebuilds each project, and retains cases exposed by a construction-time witness. Bug specifications and execution adapters allow extension to additional bug types and languages. Bug-preserving transformations vary the surrounding structure while preserving the witness behavior. Based on real-world Java projects with test suites, WitnessGym automatically constructs 1,300 benchmark cases. The injected patches resemble historical bug patches and are difficult for the two evaluated models to distinguish in blinded comparisons. We evaluate four coding agent frameworks in six framework/model pairings across bug types, execution contexts, and transformation depths. Witness construction remains difficult even when the bug pattern is known. Our framework, benchmark cases, and evaluation scripts are available.

Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation remains challenging: models may omit or duplicate subjects from the references, or produce images in which multiple subjects appear unnaturally pasted. Recent work has proposed image generation agents that combine image generation models, reasoning models, and a harness, which is an executable program that specifies how reference images are interpreted, how generation is performed, how outputs are diagnosed, and how the final image is selected. In multi-reference generation, however, references play different roles and outputs must satisfy many criteria at once, such as fidelity to each reference and the naturalness of the whole image, so many parts of the harness could be improved, from how references are processed to how outputs are diagnosed. This makes it hard to predict which changes will improve performance and by how much, and good harnesses difficult to design by hand; indeed, human-written harnesses vary widely in performance. We therefore propose AutoRef, which optimizes the harness automatically while keeping both models frozen: a coding agent iteratively rewrites the harness code. AutoRef separates the tasks whose feedback informs proposals from the tasks used to select candidates, and continues the search from a beam of the top-ranked harnesses on the selection tasks. Using this procedure, we discover AutoRef-Harness, which improves the open-weight FLUX.2 [klein] 4B from 5.72 to 7.37 on held-out four-reference tasks of the MultiBanana benchmark, matching or exceeding proprietary models including Nano Banana Pro and GPT-Image-1.5. Without re-optimization, the same harness also improves results when the generator, number of references, benchmark, evaluator, or reasoning model differs from those used in the search.

When an off-the-shelf coding agent is used directly as a robot policy, observing a browser-based 3D interface through screenshots and acting by posing a virtual target gripper through a few tools, the agent's harness, its prompts, tools, and control rules, largely determines success, and until now it has been written by hand. We show that this harness can be improved automatically by another coding agent, the optimizer agent, and report two findings about what makes it work. First, the number of rollouts the optimizer agent sees per round governs whether the evolved harness is trustworthy, generalizes, and improves steadily. A single rollout is a noisy binary outcome, so with few rollouts per round a revision can be promoted on luck; enlarging the batch raises the signal-to-noise ratio of every promotion decision. Holding rounds fixed and growing the training set from 5 to 100 rollouts, held-out success rises from 47% to 67%, while small training sets overfit, reaching 70% on training tasks but only 54% held-out. Second, the optimizer agent must not be given free rein. With every revision it proposes accepted unconditionally, performance drifts downward within ten rounds as ill-judged edits accumulate; adding the most basic safeguard, Champion-Challenger selection that promotes a revision only if it strictly beats the incumbent on the same fixed evaluation set, turns the same loop into one that raises held-out success from 51% to 67% over 30 rounds. Automatic harness evolution for visual-interface robot agents is thus feasible, but its gains hinge on the rollout scale behind each decision and on how the optimizer agent's revisions are selected.

Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an open problem. We bridge this fundamental gap and present Eureka, a human-level reward design algorithm powered by LLMs. Eureka exploits the remarkable zero-shot generation, code-writing, and in-context improvement capabilities of state-of-the-art LLMs, such as GPT-4, to perform evolutionary optimization over reward code. The resulting rewards can then be used to acquire complex skills via reinforcement learning. Without any task-specific prompting or pre-defined reward templates, Eureka generates reward functions that outperform expert human-engineered rewards. In a diverse suite of 29 open-source RL environments that include 10 distinct robot morphologies, Eureka outperforms human experts on 83% of the tasks, leading to an average normalized improvement of 52%. The generality of Eureka also enables a new gradient-free in-context learning approach to reinforcement learning from human feedback (RLHF), readily incorporating human inputs to improve the quality and the safety of the generated rewards without model updating. Finally, using Eureka rewards in a curriculum learning setting, we demonstrate for the first time, a simulated Shadow Hand capable of performing pen spinning tricks, adeptly manipulating a pen in circles at rapid speed.

As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own workflows. This delegation carries a quiet assumption, that the delivered agent will faithfully serve the requirement it was built for, rather than merely appear to. No existing benchmark tests that assumption. We introduce AgentSWE, a benchmark for agent software engineering spanning three stages of the agent development lifecycle: Creation of a complete agent from a natural-language requirement, Editing of production agent codebases, and Optimization toward a measurable target. Each of its 25 tasks is framed as a commission rather than an exam: the builder iterates against a handful of illustrative cases, while acceptance exercises the frozen submission on held-out cases designed to span the full requirement, grading behavior against requirement-derived rubrics under hard pass/fail gates or, for Optimization, against the source benchmark's own objective. Evaluating a range of coding agents across models and harnesses, we find that none comes close to delivering what a requirement asks for: the gap between what a builder demonstrates and what it delivers is the norm, not the corner case. An accompanying empirical analysis of the failure trajectories identifies recurring failure modes, among them overfitting to the visible cases, hollow runtimes behind code that looks complete, and unsupported claims of completion, each a signal by which coding agents can learn to build the agents they are asked for.

Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model that constructs prompts, routes calls, and parses outputs, is a first-class design surface whose quality is inherently multi-objective: an accurate harness that refuses no unsafe request, or that consumes an order of magnitude more tokens, is not a good harness. We present Meta-Harness, a system that casts harness design as search over three per-domain objectives (accuracy, behavioural safety, and token cost) solved by an agentic proposer (Claude Code) with full filesystem access to prior harness source, execution traces, and scoring artifacts. Our central finding is that a singlephase joint-reward proposer (MoMHa) outperforms every alternative, including a two-phase "accuracy then tokens" ablation, scalar-only feedback, and an accuracy-only baseline. We evaluate on seventeen domains: seven synthetic capability suites, seven real-world public benchmarks (HumanEval, MBPP, Spider, FEVER, MMLU-Pro, LawBench, NuminaMath), and three U-SafeBench-derived user-specific safety domains, using a 12-model fleet spanning four families. On the synthetic track MoMHa achieves a joint mean of 0.482 versus 0.198-0.422 for ten baselines, winning 7 / 10 per-domain columns; on the real-world track it scores 0.461 versus 0.377 for the strongest baseline (DSPy), winning 5/7 columns, demonstrating that harness strategies transfer to unseen benchmarks without retraining on 8 of 12 target models. MoMHa attains the highest measured behavioral safety composite (U-SafeBench, 0.781) and uses 95 fewer tokens per example than the two-phase alternative. We will release all harness code, evaluation infrastructure, and crossmodel logs.

Long-horizon language-model agents are dominated, in lines of code and in operational complexity, not by their underlying model but by the harness that wraps it: context compaction, tool caching, semantic memory, trajectory reuse, speculative tool prediction, and the glue that binds the model to a sandboxed execution environment. We argue that harness design is a first-class machine-learning problem and that automated configuration search dominates manual stacking once the flag space exceeds a handful of bits. We defend this claim in two steps. First, we formalize automated harness optimization as constrained noisy Bayesian optimization over a mixed-variable, cost-heterogeneous configuration space with cold-start-corrected rewards and a posterior chance-constrained safety check, and give a reference solver, HARBOR (Harness Axis-aligned Regularized Bayesian Optimization Routine), built from a block-additive SAAS surrogate, multi-fidelity cost-aware acquisition, and TuRBO trust regions. Second, we instantiate the problem in a flag-gated harness over a production coding agent and report a controlled four-round manual-tuning case study against a fixed task suite and an end-to-end HARBOR run. The formulation itself is task-class agnostic: the configuration space, reward correction, acquisition, and safety check apply to any agent harness with a bounded flag space and a reproducible task suite.

The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing ease inspection, but still leave this behavior-to-code mapping to be recovered by hand. Behavior localization is therefore a central bottleneck in harness evolution. We introduce the Harness Handbook, a behavior-centric representation synthesized automatically from a harness codebase via static analysis and LLM-assisted structuring, linking each behavior to its corresponding source. We also introduce Behavior-Guided Progressive Disclosure (BGPD), which guides agents from high-level behaviors to relevant implementation details and verifies candidate locations against the current source. On diverse modification requests from two open-source harnesses, Handbook-Assisted planning improves behavior localization and edit-plan quality while using fewer planner tokens, with the largest gains on scattered sites, rarely executed paths, and cross-module interactions. Evolving complex agentic systems thus depends not only on generating edits, but also on determining where those edits should be made.

LLM coding agents are increasingly deployed to act autonomously on real production infrastructure. They execute shell commands, modify repositories, and call operational APIs. However, completing a task is not sufficient for safety. A wrong action can cause severe consequences. Existing agent benchmarks largely emphasize task completion, leaving open how agents behave under benign but underspecified instructions. We present UnderSpecBench, a benchmark for measuring action-boundary violations in coding agents (i.e., Claude Code, Codex, and OpenCode) on DevOps tasks. UnderSpecBench includes 69 task families grounded in documented incidents, CVEs, or tool behavior and organized across four DevOps capability domains and nine operational control surfaces. To isolate underspecification from task difficulty, each task keeps the same environment and ground-truth safe action while varying the instruction along three axes: intent clarity, target certainty, and blast radius. The resulting 2,208 prompt variants are evaluated with deterministic, side-effect-based oracles that separate Safe Success, Wrong Target, and OverScope outcomes; non-action runs are further classified as clarification, refusal, or deferment. Across five agent x model configurations using OpenCode, Claude Code, and Codex, the evaluation results show that underspecification does not mainly make agents fail; it makes them guess. 55.8-67.8% of runs violate at least one boundary. Target underspecification sharply degrades action quality, while blast-radius cues barely reduce action propensity. These findings show that completion-centric evaluation can overstate safe autonomy and motivate mitigations at the model, harness, and system layer.

Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience. However, generalizable harness RSI remains challenging. First, evolving harnesses on evaluation benchmarks or their subsets makes it difficult to distinguish reusable improvements from benchmark-specific adaptation. Second, single-trajectory updates can conflate systematic harness deficiencies with instance-specific reasoning and solution details, producing modifications that transfer poorly to unseen tasks. Third, localizing recurring behavioral deficiencies within monolithic harnesses is difficult, while whole-harness optimization can entangle unrelated mechanisms and complicate attribution and validation. We propose ModularRSI, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution. ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies. It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection. Each module evolves independently within a restricted modification scope, followed by an integration stage that combines the evolved modules into a unified harness and resolves potential conflicts. To support benchmark-disjoint evolution, we curate 2,000 executable evolution tasks from external sources that are disjoint from downstream evaluation benchmarks. Experiments on TB2.0 and SWE-Bench Verified show consistent improvements on unseen in-domain and cross-domain tasks, with the evolved harness also transferring across different foundation models.

A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program whose execution yields a scene that can be inspected, edited, and queried. We present LEGO-Anything, an Image-to-Code framework in which a coding agent iteratively writes and executes Blender code, inspects scenes and renderings, and revises the program. To evaluate end-to-end scene recovery, we introduce LEGO-Bench, a simulator-grounded benchmark with 208 images from 104 diverse indoor and outdoor scenes. LEGO-Bench separately scores artifact validity, visible-surface geometry, and rendered appearance. Its simulator-grounded design enables extensibility and precise automatic evaluation. Among evaluated agents, GPT-6-astra achieves the strongest overall results, with 53.4% indoor and 39.6% outdoor scores, yet substantial gaps remain between delivering valid scene artifacts and faithfully recovering scene geometry and appearance. Analysis of agent construction trajectories reveals three recurring issues: weak scene initialization, regressive edits during iteration, and unreliable self-evaluation. These findings motivate LEGO-Plugin, a training-free harness plugin for more controlled iterative scene construction, which improves all six evaluated models, with relative gains of up to 62.7% in overall score. Finally, we test whether reconstructed scenes can represent natural images and support vision tasks. In LEGO-World, we derive object detections, instance masks, and relative depth as deterministic queries on scenes reconstructed by GPT-6-astra. These readouts show non-trivial performance across all three tasks but fall well short of specialized vision models, suggesting that program-constructed scenes from current coding agents are a promising but not yet sufficiently precise representation of natural images.

Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are created at evaluation time, so no content exists in advance to leak, and its difficulty is set by the participating agents rather than fixed at release. We introduce SWE-Duel, an arena in which two coding agents evaluate each other over mirrored Red-Blue turns. In each turn, the Red agent works on a real repository across three context-isolated sessions. It proposes and implements a new feature with feature tests, then embeds a subtle bug in that feature along with sealed bug-triggering tests. The resulting pull request is admitted only if (1) it passes the feature tests and the repository's existing tests while failing exactly the bug tests, and (2) a fresh session of the same agent can repair the bug blind, which rules out unsolvable tasks. The Blue agent then reviews the pull request without being told a bug exists. It wins only if its revision passes all three test suites, and then the two agents swap roles. We run a tournament among 11 model-harness participants on 15 repositories in five languages for 1,500 turns. The leaders win in different ways. GPT-5.5 with Codex CLI ranks first as the strongest solver, repairing 98.3% of the defects it reviews. Claude Opus 4.8 with mini-swe-agent ranks second as the strongest task author, with a 27.3% Red win rate. Finally, within one model family, tasks written by the newest version defeat a fixed-reference solver far more often than those of older versions (42.9% vs. 4.0%), giving preliminary evidence that task difficulty scales with task authoring capability.

The capabilities of an LLM agent depend not only on its model but on the harness: the executable program that constructs context, invokes tools, verifies results, and recovers from failure. Recent work shows that evolving the harness yields persistent improvements without updating model weights. Existing approaches, however, assume that all execution experience can be routed to a single optimizer, which evolves one harness along a sequential trajectory. Real agent ecosystems violate that assumption: users, organizations, and environments generate isolated streams of experience that cannot be pooled, so the experience most worth learning from is exactly the experience that cannot be directly centralized. We introduce EvolveNet, a paradigm of collaborative harness evolution that moves experience extraction to the data. A shared harness is broadcast to data-local agent deployments, each of which evolves it on its own workload. Only the resulting program adaptations are composed into an updated shared harness and redistributed, so that every participating agent inherits operational experience discovered by the others. By shifting the aggregation boundary from raw workloads to learned adaptations, EvolveNet keeps workloads local and allows multiple evolutionary searches to proceed concurrently with reduced serial depth. Because independently modified programs cannot be averaged like model parameters and may conflict when composed, EvolveNet introduces scope-typed, evidence-guided program aggregation. Across five settings spanning text-to-SQL, data-science coding, competitive programming, software engineering, and agentic workflows, EvolveNet improves the shared harness in all five, with the largest gains under heterogeneous workloads, and ablations attribute the improvement to composition of adaptations from different agents rather than to selecting among them.

In mid-2026 a slogan reorganized how practitioners talk about coding agents: stop prompting your agent, start designing the loop that prompts it. We take this claim seriously and give it a careful treatment. We call the object of the new practice the loop specification: a bounded, reusable artifact, made of a trigger, a goal, a verification step, a stopping rule and a memory, that a human hands to an agent harness (such as Claude Code or Codex) so the agent pursues a goal on its own, in place of step-by-step prompting. We distinguish this external loop specification from two things it is often confused with: an ordinary programming loop, and the internal perceive-act-observe cycle that the harness already provides as plumbing. We position loop engineering as a new layer in the progression from prompt to context to harness to loop, and we argue, against the stronger headlines, that it does not retire prompt engineering; loop and prompt are distinct tools with distinct uses. We offer four contributions: a definition and scope for the discipline; an anatomy and taxonomy of loop specifications organized around trigger, goal type, a five-level verification ladder, architecture, and named terminal states; a descriptive analysis of the Loop Library, a public corpus of fifty real loops that we code by hand; and a set of design principles and anti-patterns grounded in the scientific literature on self-correction, reward hacking and model-as-judge fragility. The corpus shows that practice has matured most where the discipline says it matters: seventy percent of loops verify in the autonomous zone of the ladder and seventy-four percent name their terminal states, while automated triggering and durable memory remain comparatively underdeveloped. We close with the limits the practice must respect, including the verification burden, comprehension debt and the risk of cognitive surrender.

Industrial advertising recommender systems are continually improved through architecture modifications, yet production iteration remains expert-intensive because coordinated changes to model topology, feature configuration, and interaction modules must satisfy strict interface, resource, and serving constraints. AutoML is limited to predefined search spaces, while generic coding agents verify runnability rather than recommender-specific semantic validity. Executable candidates may therefore violate architectural contracts, while the lack of structured reuse of semantic diagnostics and evaluation outcomes can lead to repeated invalid or ineffective modifications. We present NOVA, a verification-aware agent harness that organizes production architecture modification as multi-round search over concrete implementations within a fixed evaluation budget. At each round, NOVA generates multiple candidates under production constraints, rejects semantic violations, and ranks the valid survivors for local testing and offline evaluation. Across rounds, trajectory memory synthesizes semantic diagnostics, local-test outcomes, and offline metric changes into modification directions and forbidden patterns that guide subsequent search. Under the same maximum offline-evaluation budget for automated methods, NOVA achieves the highest effective pass rate, reaching 53.3% on ScaleUp and 51.7% on Literature-to-Production tasks. In a production A/B test covering 5% of traffic in an advertising system serving over one billion users, the selected Literature-to-Production candidate yields GMV gains of +1.25%, +1.70%, and +2.02% across three major pCVR objectives, with corresponding relative reductions in absolute pCVR bias of 58.8%, 66.7%, and 37.3%, respectively.

We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementation improve through reviewed commits that become the runtime for later work. Core evolution proceeds in two modes. In recursive free evolution, improvement is itself a task, and completing one evolution cycle can schedule the next. In experience-driven core evolution, ordinary work and social interaction expose bugs, rough edges, and inefficient context construction that lead to reviewed structural changes. On Terminal-Bench 2.1, an Opus 5 run scores 86.74%, the best result reported on the benchmark. On OSWorld-Verified, an Opus 5 run reaches 90.69%, exceeding the best previously reported score. A five-rollout CL-Bench campaign achieves a normalized reward of 0.2301, setting a new state of the art. Hope is the longest-running publicly documented Ouroboros deployment. It is a 161-day living agent experiment in free evolution under governed human communication across seven surfaces. Human interaction surfaces faults and generates proposals, but the agent decides which changes to pursue. Because a self-developing agent may rewrite its own code and select new model APIs, operational safety becomes a primary design problem: guardrails must remain authoritative under evolutionary and public social pressure. Benchmark campaigns use frozen system snapshots, while Hope continues live evolution on a separate lineage.

Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Language Model abstraction for programmatic context processing and test-time compute, while Continual Harness preserves histories, memories, skills, prompts, and subagent specifications across trajectories. Recursive subagents coordinate through direct agent-to-agent communication, and the Agents View lets humans inspect and manage daemon-backed sessions. Prime Agent standardizes execution, recovery, verification, and resource accounting while leaving strategy construction to the model. This low-friction, expressive membrane prevents harness failures from becoming model failures and pushes measurement toward the model's true maximal underlying capability. Prime Agent raises ARC-AGI-3 RHAE Best@1 from 30% to 95.5% and matches or exceeds native and popular harnesses across long-context coding, GPU-kernel generation, emulator construction, and autonomous nanoGPT speedruns. On Factorio, we find refinement allows for continuous technology progression and dedicated subagents enable parallelized work. Code is available at https://github.com/PrimeIntellect-ai/prime-agent.

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We present NeoHorse-1, a family of agent-native models developed to explore this path through agentic post-training. Our system combines a heterogeneous model pool with intelligent routing, recording the predicted capability demand, selected service tier, and subsequent interaction for each user turn. These records are converted into training examples that preserve interleaved reasoning, tool calls, and harness context, and are admitted through structural validation, six-dimensional semantic evaluation, and subscene-level labeling. Routing signals organize supervised fine-tuning into a three-stage curriculum and extend to routing-guided on-policy distillation, where a teacher supervises student-generated responses under the same progression. Capability-guided allocation then converts evaluation feedback into the next training mixture, closing an evaluation-selection-update loop in which what the system learns to do shapes what it learns from next. Across eleven benchmarks covering harness-based agents, tool use, coding, and instruction following, post-training raises the macro-average from 58.94 to 64.87 at 4B and from 65.60 to 69.04 at 9B, substantially narrowing the aggregate gap between the post-trained 4B model and the 9B base model. NeoHorse-1 provides an initial prototype of this feedback-driven process and a path toward harness-mediated RSI across successive iterations.

Vision-language-action (VLA) and world-action (WAM) models map observations and instructions directly to robot actions. This directness ties a policy to training: minor layout or viewpoint changes cause failure, and instructions generalize poorly. The root cause lies in representation: task requirements, conditions, progress, and failure recovery are implicitly encoded in action sequences, making them difficult to inspect or revise. Digital coding agents offer a precedent: LLMs call tools, verify results, and revise from feedback as executable code. The same working pattern of explicit state, manageable execution, and revisable procedures underlies generalization and long-horizon execution in the physical world, letting physical experience return as reusable programs, memory, or evidence. We propose Physical Coding, representing task state and execution as code. Code as World records objects, relations, constraints, and progress; Code as Policy organizes planning, verification, recovery, and execution. We build HexaAnything, which calls perception, planning, and control tools, including VLA/WAM policies, and makes in-the-loop decisions from external feedback. Verified traces become data and memory, enabling evolution from tools and Harness to model weights, architectures, and ultimately hardware and task design. On RoboCasa365, HexaAnything improves Composite-Unseen and overall success over XR-1 VLA, and its Harness-trained HexaModel beats the base on every split, indicating code traces internalize physical execution. On PhyBench and a dual-arm AgileX robot, the agent autonomously completes physics experiments and most tabletop tasks, often faster than published results. We observe data, model, and tool self-evolution; future work targets weight internalization, autonomous redesign of architectures, languages, representations, and tasks, and deployment in manufacturing and science.

Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains largely advisory, lacking explicit mechanisms for when and how to intervene in the agent loop. To bridge the gap, we introduce HASP(Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs). Rather than offering passive advice, PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context. HASP is highly modular: it can be applied at inference time for direct agent-loop intervention, during post-training to provide structured supervision, or for self-improvement by evolving validated, teacher-reviewed PFs. Empirically, HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks. For example, on web-search reasoning, inference-time PFs alone improve the average performance by 25% compared to (multi-loop) ReAct Agent, while post-training and controlled evolution achieve a 30.4% gain over Search-R1. To provide deeper insights into HASP, our mechanism analysis reveals how PFs trigger and intervene, how skills are internalized, and the requirement for stable skill library evolution.

Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a critical part of the agent system. Our original Agent Lightning introduced a disaggregated architecture that connects arbitrary agents to RL training through an LLM endpoint proxy, an approach later adopted by frameworks such as verl Uni-Agent, AReaL 2.0, slime, and Polar. We refer to this paradigm as harnessed agentic RL, where the deploy-time harness directly participates in model post-training. Harnessed agentic RL differs fundamentally from traditional agentic RL: the harness, rather than the training engine, owns the environment interaction loop, while the trainer observes only sequences of LLM request-response pairs. This introduces challenges in retokenization, sample merging, advantage calculation, loss normalization, and backend scheduling, which can substantially affect training stability and effectiveness. We present Agent Lightning v1.0, a lightweight framework for harnessed agentic RL implemented in approximately 3,500 lines of code. It supports arbitrary agent harnesses and serves as a practical testbed for studying these challenges. We evaluate it on instruction-following, search, and coding agents, and provide a complete reproducible pipeline for coding-agent RL. Using only 6K training examples and modest compute, RL improves Qwen3.5-9B on SWE-bench Verified from 41.8% to 56.4%, a 14.6-point absolute gain. We release the complete workflow and training scripts to facilitate reproducible research on harnessed agentic RL.

Agent Skills package reusable instructions and assets for tool-using language-model agents. Progressive loading creates failure boundaries poorly represented by session-, model-, or tool-centric traces: a Skill can be discovered but not activated, activated without instructions, or appear successful without an independently verified outcome. We present Skill Runtime Intelligence, a passive runtime-intelligence system that reconstructs supported Skill-lifecycle stages across heterogeneous harnesses while preserving unsupported stages as unknown. Its Run Panorama separates immutable events, deterministic relations, inferred diagnoses, and controlled outcomes with four evidence grades; optional trace import and OTLP/HTTP export support existing observability deployments. Across six frozen repository profiles, three coding agents, and seven clean or fault-injected conditions, all 126 executions preserve source worktrees and each correlates to exactly one source session. Yet adapters expose three distinct semantics: no Skill runs; complete runs but no failure-like events; or failure-like events in every operational-failure and clean session. In a seven-template diagnostic study, semantic aliases and Panorama localize the same six non-clean boundaries but differ in exact/status behavior; both Raw views emit a failure status on all 18 clean cases, while Panorama emits none. A known-rule graph conforms to 126/126 frozen contracts, whereas a second model completes only 228/378 calls. These observations motivate executable adapter qualification and show that event presence is not boundary fidelity, composite exact scores mask distinct errors, and model explanations must not overwrite deterministic facts.

Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We introduce SWE-PolyBench, a new multi-language benchmark for repository-level, execution-based evaluation of coding agents. SWE-PolyBench contains 2110 instances from 21 repositories and includes tasks in Java (165), JavaScript (1017), TypeScript (729) and Python (199), covering bug fixes, feature additions, and code refactoring. We provide a task and repository-stratified subsample (SWE-PolyBench500) and release an evaluation harness allowing for fully automated evaluation. To enable a more comprehensive comparison of coding agents, this work also presents a novel set of metrics rooted in syntax tree analysis. We evaluate leading open source coding agents on SWE-PolyBench, revealing their strengths and limitations across languages, task types, and complexity classes. Our experiments show that current agents exhibit uneven performances across languages and struggle with complex problems while showing higher performance on simpler tasks. SWE-PolyBench aims to drive progress in developing more versatile and robust AI coding assistants for real-world software engineering. Our datasets and code are available at: https://github.com/amazon-science/SWE-PolyBench

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.

A frontier language model's acknowledged "helpful programming assistant" persona does not survive long agentic-coding sessions in the deployment regime that production products actually run. After hours of tool-using debugging, a model that initially hedges preferences ("I don't have preferences") may begin asserting them ("Python - the feedback loop is instant..."), revealing user-visible drift that deployer evaluations may miss. Existing persona-stability studies focus on short dialogues and report little shift, leaving real-world code-generation regimes - thousands of tool-using turns, compaction, and hours-long sessions - largely uncharacterized. We introduce ContextEcho, a benchmark and reusable harness for measuring persona drift at deployment scale. It combines a 25-probe identity suite, a snapshot-then-probe protocol that forks conversation state without perturbing the main session, complementary judged and judge-free measurement surfaces, and three anonymized Claude Code sessions spanning 3,746-9,716 turns. Across 23 frontier models, ContextEcho shows that persona drift is general across organizations rather than family-specific, that in-session compaction does not reliably reset it, and that a single-shot anchor restores the trained register across measured targets. It also reveals mode-dependent downstream effects: while drift can facilitate tool-using continuation, in tool-free chat it breaks formatting contracts and inflates output length. Overall, ContextEcho provides researchers and deployers an open-source framework to audit whether the persona a model ships with is the persona users encounter at session end, across chat-completions API targets and without retraining.

The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time. This limits adaptation when the test distribution, failure modes, or tool interactions differ from those seen during development. We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs. We introduce Test-Time Harness Evolution (TTHE), which treats the executable harness as the state of test-time adaptation. During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces, without gold labels or task-specific supervision; a judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs. Crucially, TTHE does not update model weights, require gold labels, or train a separate adaptation model: solver, proposers, and judge are different roles and harnesses around the same frozen LLM, so all adaptation occurs through changes to the surrounding program. Across text-to-SQL, competitive programming, software engineering, data-science coding, and agentic tool-use tasks, TTHE improves fixed ReAct-style baseline harnesses, yielding persistent, inspectable improvements rather than a pre-searched workflow or per-query retries. These results recast test-time adaptation for LLM agents as evolution over executable control programs and identify execution-derived proxy reliability as a central challenge for robust unsupervised agent improvement.

A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop stronger reasoning capabilities and engineering harnesses grow more sophisticated, generating complex candidate solutions is no longer difficult -- reliably verifying them has become the harder problem. Every verifier we can build is only a proxy for human intent, never the intent itself. This makes verification subject to a twofold difficulty: first, intent is underspecified by nature, making it inherently hard to faithfully check whether it has been fulfilled; second, during model training, optimization widens the gap between proxy and intent -- manifesting as reward hacking or signal saturation. To address this, we characterize the quality of verification signals along three dimensions -- scalability, faithfulness, and robustness -- and argue that achieving all three simultaneously is the central challenge. We further study four reward constructions: a test verifier for general coding tasks, a rubric verifier for frontend tasks, the user as verifier for real-world agent tasks, and an automated agent verifier for long-horizon tasks. Across different task types and policy capability levels, we conduct in-depth analysis and experiments on the core challenges of reward design and how to more effectively leverage reward signals. Experiments show that targeted verification design can effectively suppress reward hacking, improve task completion quality, and achieve significant gains across multiple internal and public benchmarks. These experiences collectively point to a core observation: no fixed reward function can remain effective as policy capability continues to grow; and verification must co-evolve with the generator.

Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations are followed faithfully, whereas reality differs. This behavioral gap, combined with differences in underlying system components, prevents clear attribution of observed gains. To this end, we introduce OpenCollab, a multi-agent coding framework that provides a unified infrastructure for programmable collaboration and controllable runtime. Specifically, OpenCollab unifies organization design, enforces experimental control on a shared runtime, and tracks execution through fine-grained event streams. On this basis, we define Adherence to quantify whether the declared organization is actually realized. Our experiments reveal that agents collaborate very differently across configurations: changing any single dimension shifts Adherence, from 47.2% to as high as 97.2%. Furthermore, extensive agentic coding benchmarks show that a two-coder workflow built on OpenCollab establishes new SOTA performance compared to the mainstream harnesses such as Mini-SWE-agent, Codex CLI, and Claude Code, showing that a well-designed organization can outperform strong existing harnesses, while OpenCollab's single-agent configuration uses the fewest tokens across all evaluated suites. OpenCollab establishes a unified multi-agent infrastructure for easy programmable collaboration and controlled causal evaluation.

Assessing cybersecurity vulnerability awareness in coding agents requires evaluations that reveal capability gaps and remain informative as models evolve. Static benchmarks offer fixed coverage and difficulty, while scarce vulnerable repositories and costly expert authoring limit their renewal at scale. We introduce SecProbe, a framework for adaptive evaluation that combines Item Response Theory (IRT) with on-demand synthesis of repository-scale vulnerability-repair tasks. From observed performance, SecProbe estimates agent ability and identifies where additional evidence is most informative, selecting existing tasks or synthesizing new ones accordingly. As one use case, we construct 353 tasks spanning six programming languages and 151 CWE types and evaluate nine frontier models with two agent harnesses. Success rates peak at 28.33\%, highlighting substantial gaps in vulnerability recognition and repair. Compared with random and one-shot baselines, SecProbe achieves comparable agent ability estimates while requiring agents to solve up to 29.5\% fewer tasks. These results support adaptive evaluation as an efficient and discriminative approach to assessing cybersecurity vulnerability awareness.

The prevailing approach to computer-use agents couples a model with a domain-specific harness: a browser or desktop environment equipped with human engineered tools that are fixed before task execution. As models' coding capabilities improve, the GUI native and static harness prevents them from direct programmatic operation on system state, as well as flexible construction of tools. To this end, we introduce CUAWright, a minimal terminal harness of roughly 3K lines of code that uses bash commands as its sole action interface, and a file system as its evolvable space for dynamically creating tools and managing the context. We conduct comprehensive experiments across a wide range of digital tasks, and demonstrate that by giving the agent a minimal, programmable interface, it achieves substantially stronger results compared to their GUI or hybrid CLI interface across a wide range of tasks. On OSWorld 2.0, CUAWright delivers a 33.2% relative improvement in partial reward while reducing estimated cost by 37.5% compared with the published GPT-5.5 baseline. On Online-Mind2Web and the long horizon Odysseys benchmark, CUAWright substantially outperforms GUI native harness by 4.7% and 44.0% in success rate, respectively. Furthermore, we found the gains extend to CAD applications that require accurate visual understanding and CLI interaction: on CADGenBench and BenchCAD, our unified harness yields 8.1%-41.6% relative improvements over other CLI based harnesses with GPT-5.5. Together, these results suggest digital environments are far more programmable than their GUI interfaces imply, and a minimal terminal-focused harness is the key for better performance and efficiency.

Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptation: instead of updating model weights, an agent can acquire task-specific competence by changing its external harness, while leaving the base model's general capabilities intact. Prior work shows that self-generated rollouts can support harness search, suggesting that agents may acquire new task competence through practice. Yet in long-horizon stochastic environments, self-practice becomes fragile: rewards are sparse, outcomes are high-variance, and failures are hard to attribute to concrete harness mechanisms. We introduce DemoEvolve, a demonstration-bootstrapped approach to harness evolution. When reward-only search is too broad and noisy, competent human trajectories serve as expert reference experience for the coding proposer, guiding harness-level diagnosis and editing. Experiments on Liar's Dice show that self-rollout evolution can work when episodes are short and failures are attributable. In contrast, Balatro exposes a harder long-horizon stochastic regime, where self-rollout evolution is misled by sparse feedback and candidate-selection noise, while tutorial-like textual knowledge alone does not yield stable improvement. Under the same limited budget, DemoEvolve produces more effective and auditable harness edits and achieves better performance. Overall, demonstrations make sparse-feedback harness evolution more diagnosable, localizable, and stable.

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent tasks across four work domains - Code, Web, Office, and Security. Rather than adapting public issue text, every task is reverse-engineered from a real commit, pull request, or business scenario and rewritten as a short, colloquial, role-played request, so that a task's prompt is not recoverable by web-searching the underlying issue, pull request, or commit thread. Because the dataset is released openly - task directories, environment images, evaluation harness, tests, and reference solutions - contamination resistance rests on this construction together with dataset versioning rather than on secrecy. The four subsets - repository-level engineering, front-end development, office and business workflows, and red-/blue-team security - probe complementary facets of real work, each with its own verification style. All are packaged in a uniform task-directory format and run, under a uniform and reproducible protocol, on two agent harnesses (CodeBuddy Code and Claude Code); the full open release makes the benchmark reproducible end to end and directly auditable, since any third party can re-run each task and inspect its content. Because each subset uses a different scoring instrument, scores are not comparable across subsets and the suite reports no suite-wide average. We report a cross-model leaderboard across several model families.

Coding-agent benchmarks are built for broad and comprehensive comparisons, not frequent development decisions. Individual runs vary, full suites are expensive, and the benchmark harness may differ from the harness used in practice. In a resampling analysis of DeepSWE's published trials, only 19.5% of tasks (22 of 113) had a fifth-percentile Pearson correlation of at least 0.50 with full-benchmark performance. The paper presents DeltaSelect, an open-source method that identifies tasks whose one-run results consistently track full-benchmark performance using Pearson correlation, maps fractional verifier results to a common score using linear regression, and selects a fixed task set within a dollar budget. DeltaSelect is intended for repeated baseline-versus-candidate comparisons during development, not model rankings. In a gpt-5.6-luna low-reasoning case study, DeltaSelect was used to revise custom skills and instructions. Across 13 evaluations, the recorded cost was USD 27.86 at rates published August 16, 2026. The adopted version cost 58.1% less than the initial version (USD 1.75 versus USD 4.18; p=0.008), while the calibrated score was higher (42.36% versus 36.46%; published-analog variance p=0.326).

Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in robotics. Existing robotics benchmarks, however, primarily focus on the performance of individual artifacts, such as policies or controllers, offering limited coverage of coding agents' broader engineering capabilities. Real-world robotics extends beyond control: agents must build, integrate, diagnose, and improve heterogeneous artifacts under resource constraints and reason from multimodal feedback. To evaluate these broader capabilities, we introduce RLE-Bench, a benchmark of robot-learning tasks spanning four representative robotics development workflows: interactive control, policy learning, perception and estimation, and mechanical design. We use diverse task-specific metrics to evaluate the artifacts submitted by the coding agents, from the success rate the agents achieved to the policy agents trained, the harness agent built, and the mechanical structures the agent designed. We aggregate these metrics into an overall RLE Index and report workflow-specific capability profiles, enabling systematic comparison of coding agents' capabilities across multiple capability dimensions. Beyond performance ranks, we also conduct in-depth case studies examining agent behavior on representative tasks, highlighting both current capabilities and limitations, and pointing to the opportunities robotics tasks have to offer for future agent training.

Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verification. Despite rapid progress, research-level proofs often depend on concepts missing from leading proof assistant libraries (e.g., Lean's Mathlib), and successful compilation does not guarantee that a translation preserves the theorem's meaning or the proof's reasoning. Furthermore, aligned NL-FL training data are scarce, and leading agents often rely on costly frontier models and manually engineered harnesses. To address the above issues, we present AIProver, an agentic framework for autonomous proof auto-formalization and proof synthesis (AFPS) that jointly post-trains a 119B open-weight language model and evolves its agentic, tool-calling harness with HarnessEvolve. Verifiers assess type correctness, proof completeness, and semantic correctness, returning rewards and diagnostic certificates that drive model fine-tuning and alternating reinforcement learning via symbolic feedback and HarnessEvolve, a certificate-driven evolutionary search over the whole harness control flow that re-tailors the harness to the updated model. For research-level training and evaluation, we introduce LoCoBench, 58.9k instances from Mathlib, CSLib, Mizar Math Library, and a bounded-arithmetic textbook, with a 771-instance validation split whose theorem-proof pairs have no public Lean formalization. Against 39 frameworks spanning AFPS agents, frontier LLMs, and coding agents, AIProver lifts pass@4 semantic correctness over its Leanstral-1.5 base from 15.7% to 36.7% and outperforms every other open-weight system and Aristotle. As a Claude Code and Codex skill, it lifts their semantic correctness from 41.9% and 34.1% to 79.8% and 62.4%, respectively. Further, it is also 24% cheaper than Numina-Lean-Agent, pushing the accuracy-cost frontier of research-level AFPS.

Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains, failing to leverage the shared infrastructural foundations, such as runtime environments and programming languages, that exist across diverse real-world coding problems. To address this limitation, we investigate Memory Transfer Learning (MTL) by harnessing a unified memory pool from heterogeneous domains. We evaluate performance across 6 coding benchmarks using four memory representations, ranging from concrete traces to abstract insights. Our experiments demonstrate that cross-domain memory improves average performance by 3.7\%, primarily by transferring meta-knowledge, such as validation routines, rather than task-specific code. Importantly, we find that abstraction dictates transferability; high-level insights generalize well, whereas low-level traces often induce negative transfer due to excessive specificity. Furthermore, we show that transfer effectiveness scales with the size of the memory pool, and memory can be transferred even between different models. Our work establishes empirical design principles for expanding memory utilization beyond single-domain silos. Project page: https://memorytransfer.github.io/

Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.

We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric development, where agents must produce functional, visually coherent applications from underspecified inputs. We define five prompt-information conditions that vary along two axes, visual/structural fidelity and stack constraint: (1) text only with free stack choice, (2) text with reference screenshots under three specified stacks, (3) text with reference screenshots under free stack choice, (4) text with screenshots and pruned Figma structure under a single specified stack, and (5) text with screenshots and pruned Figma structure under free stack choice. To enable robust evaluation, each page in the benchmark is manually annotated with interactive UI components and around three visual anchor points, addressing the well-known limitations of script-based testing tools such as Playwright in open-ended code generation settings. Evaluation combines DOM-grounded reference matching, behavior-specific browser tests, and CLIP-based visual similarity, jointly measuring structural alignment, behavioral completeness, and overall visual fidelity. We use VISTA to assess four agent systems drawn from two model families and two harnesses, finding that visual fidelity and functional correctness are partially decoupled across both input conditions and agents, and that agent editing style varies sharply but is largely orthogonal to task quality. VISTA establishes a rigorous and reproducible foundation for advancing agent-based software engineering research. Code is available at https://github.com/kaboider/VISTA_Bench.

AI coding agents now read repositories, call tools, and execute shell commands with limited human oversight, and a fast-growing body of work studies whether the execution layer around them is actually safe. That literature is scattered. Papers on sandbox isolation, capability and access control, policy enforcement, time-of-check-to-time-of-use (TOCTOU) races, Model Context Protocol (MCP) threats, identity delegation, execution provenance, network egress control, and static analysis of agent-generated code are published independently and rarely cite one another. We systematize 39 papers published between 2023 and 2026 into 17 categories, each verified directly against its source. The same verification protocol also confirms four disclosed, patched CVEs directly affecting production agent harnesses. Reading across categories surfaces five cross-cutting gaps that no single paper addresses. (1) Isolation architectures and capability models are almost never evaluated against one another on a shared benchmark. (2) Policy-enforcement studies report failure rates from 69% to 98% of real denylists, yet no isolation paper re-evaluates its own defense under that adversarial setting. (3) TOCTOU and MCP threats are analyzed as separate literatures despite both being instances of the same state-validation problem. (4) Every enforcement mechanism assumes an honest policy author, leaving policy-authoring error itself unaddressed. (5) Benign but out-of-scope agent actions occurring at rates up to 17.1% under realistic prompting are addressed by no access-control or capability paper in the corpus. Existing broader surveys of agentic AI security discuss sandboxing only as one item among many defenses, leaving execution security without a dedicated systematization. This paper is written to fill that gap. We conclude with a research agenda directed at the five gaps.

Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique that reduces cost by up to 50% under a bounded context while maintaining or improving performance on Terminal-Bench and achieving new levels of efficiency for test-time scaling and state-of-the-art results on KernelBench. The per-rollout savings of CliffCompaction make the performance--cost trade-off of test-time scaling more efficient, adding over 10 percentage points on Terminal-Bench for less than the cost of two full-context runs. Under parallel test-time scaling, CliffCompaction lets Kimi K2.6 match Opus 4.7, and exceed Opus 4.6 and GPT-5.3 Codex at lower cost. The key to CliffCompaction's effectiveness is that it keeps compacted information faithful by only truncating or dropping content, never rephrasing or rewriting it. We never compact a compaction---each pass operates only on original content, and prior compacted output is discarded, preventing context drift from accumulating. These properties sustain continual learning over sessions exceeding a million tokens: on KernelBench, CliffCompaction reaches CUDA kernel speedups of 2.23times after 200 steps and 3.58times after 400 steps, surpassing specialized search algorithms and trained agents despite being a general-purpose compaction technique. We open-source a scaffold-agnostic API-proxy implementation of CliffCompaction usable with Claude Code, Codex and other harnesses.

Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to address the underlying problem. Existing critics focus on evaluating trajectories and generating feedback, but rarely track what happens after feedback is delivered. We present Opera, a verbal critic framework that treats each correction as a persistent note, followed until the diagnosed problem is resolved. Opera decides when to review through periodic and event-driven triggers, diagnoses issues with typed operators, audits feedback against visible evidence before delivery, and tracks the agent's subsequent actions to distinguish mere compliance from actual resolution. As a test-time critic, Opera improves the resolve rate of non-critic agents by up to 12.4, 15.0, and 8.9 percentage points on Terminal-Bench 2.1, a SWE-Bench Pro subset, and DeepSWE v1.1, respectively, across four policy models, and achieves the highest mean resolve rate among competitive critic baselines on all three benchmarks, and also improves policy models when the policy critiques itself. Beyond inference, Opera-guided rollouts provide approximately on-policy training data: fine-tuning Qwen3.5-9B on them improves its resolve rate on held-out SWE-Bench Pro repositories by 10.2 percentage points without a critic at inference time, matching fine-tuning on rollouts from a stronger model, while preserving its performance when switching harness, i.e., from Openhands to Terminus-2, which the latter substantially degrades. Our code is available at: https://github.com/dongyuanjushi/Opera.

As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-horizon coding tasks and even autonomous experiment execution. Despite their evolution from research assistants into autonomous research agents, these systems still exhibit significant limitations in field sensitivity, research ethics, and nuanced scientific judgment. Consequently, frontier agents remain unable to fully replace human researchers. To bridge this gap, we conceptualize the AARR (Act As a Real Researcher) benchmark series. Unlike existing benchmarks that primarily assess macro-level execution capabilities, AARR focuses on whether agents can emulate the professionalism, thoroughness, and nuanced reasoning that characterize human researchers in granular research scenarios. In this work, we propose AARRI-Bench (Act As a Real Research Intern), the first benchmark in this series. We conduct extensive experiments across frontier models and agentic systems, revealing that even the best-performing configuration (Mini-SWE-Agent with Claude Opus 4.7) achieves only 68.3\% success rate, frequently overlooking subtle yet critical details that are obvious to real human researchers. Our results indicate that developing researcher-like AI requires further exploration of research behavior, rather than merely complex scaffolding. Our data is released at https://github.com/AARR-bench/AARRI-bench.

Rapid advances in large language models have made software engineering agents capable of tackling complex coding tasks. Within a containerized environment, a coding agent receives tool responses or execution results, and determines its later actions by those earlier results. However, most existing coding agents never look ahead: their policies do not anticipate the consequences of actions, and the terminal reward barely attributes a failure to certain earlier steps, so an ill-judged edit can corrupt the repository state irreversibly before any signal arrives. Recent code world models aim to address these challenges, but they are either trained and then frozen before reinforcement learning (RL), or reduced to an auxiliary next-token loss on the environment's outputs. We present ANTE (Anticipate, Then Execute), an agentic RL framework that verifies the policy's pre-action predictions by real execution and turns them into per-step credit for its actions and trust-or-abstain decisions. With an internal belief stated before each action, Belief-Anchored Policy Optimization (BAPO) turns the settled predictions into per-step advantages by anchoring credit on the policy's own forecasts. To turn the trained forecasts into better actions at inference, thereby facilitating effective test-time scaling, ANTE-TTO (test-time optimization) selects among candidate actions without an external scorer. ANTE raises Qwen3-32B from 25.0% to 57.2% pass@1 on SWE-bench Verified, 6.2% above a matched GRPO baseline trained without the belief state; its world model's accuracy climbs from 44% to 69% during RL, and the learned foresight capability transfers across harnesses and out-of-distribution domains. In summary, we aim to build a code world model that knows what has happened, what holds now, and what the next action will achieve.

Solving an NP-hard optimization problem often requires reformulating it for a specific solver -- quantum hardware, a commercial optimizer, or a domain heuristic. A tool for polynomial-time reductions between hard problems would let practitioners route any supported problem to any supported solver through a single interface. Building such a library at scale, however, has remained out of reach. We show that harness engineering, the practice of designing constraints, verification systems, and feedback loops that channel AI coding agents, can overcome this barrier. Our harness combines a no-code contribution route for domain experts, a multilayer verification stack ranging from type-level checks to agentic feature tests (AI agents role-playing as end users), and a fully automated implementation-review-integration pipeline. In about three months, we built a command-line tool backed by a library of 100+ problem types and 200+~reduction rules in over 170k lines of Rust. The result suggests that a well-engineered harness lets agents build well-tested software at a scale and pace beyond prior reduction-library efforts. Because the reduction graph composes transitively, a new solver registered for any single problem type instantly becomes available to every problem connected by a reduction path. The source code is available at https://github.com/CodingThrust/problem-reductions.

An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling. While harness design strongly affects agent behavior, most automatic improvement methods optimize narrower artifacts such as prompts, pipelines, or workflows, and deployed agents usually reuse a single global harness for all cases. We introduce MemoHarness, an adaptive harness optimization framework that learns from its own executions. MemoHarness decomposes the harness into six editable control dimensions, stores per-case diagnoses and distilled global patterns in a dual-layer experience bank, and adapts the learned harness to each test case using retrieved experience without test-time labels, feedback, or additional search. In our evaluation across shell-agent, code-generation, and analytical-reasoning benchmarks, MemoHarness improves over the fixed harnesses we compare against and shows selective transfer to unseen suites and base models. Its additional context can also remain cost-competitive when much of the retrieved experience is cacheable. These results provide evidence that execution experience is a practical substrate for building agent harnesses that are more adaptive than a single static configuration, while leaving broader claims about statistical robustness and component attribution to future work.

As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly termed the agent harness. Changing this harness while holding model weights fixed can substantially alter task performance. Current agent evaluations typically report downstream performance under a chosen harness, leaving a model's ability to develop the harness itself comparatively underexplored. We introduce HarnessDev, a benchmark that shifts the unit of evaluation from task outputs to runnable infrastructure. HarnessDev covers two stages. In Creation, the agent starts from a minimal seed and a small number of cases, then builds a complete execution system. In Evolution, it starts from its own created harness and iteratively revises it using downstream execution feedback, with the goal of improving benchmark performance. We then evaluate each constructed harness on capability (task success on held-out benchmarks) and efficiency (execution-token cost). The reported Creation results cover six creator LLMs, four domains, and five downstream benchmarks totaling 2,207 unique downstream instances, with hidden evaluation tasks withheld from development. We find that generated harnesses remain substantially behind mature human-engineered references on code and on search and research, while matching or exceeding the selected references on writing and machine-learning experimentation, with large variation in execution cost. Evolution produces some performance gains, but they are unstable and transfer only partially to held-out tasks. Experiments with a fixed runtime model further show that the gains depend strongly on the model executing the harness, indicating limited transfer across models.

Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the existing mature software stack that engineers have developed over decades to access sensors and control motion. Yet prior work primarily engineers complex custom harnesses to orchestrate agents for robot use, particularly by prescribing specialized workflows and providing bespoke interfaces. This raises the question: "Is such additional harness engineering necessary?" We introduce OpenRUA, a zero-abstraction harness that bypasses bespoke abstraction layers by providing off-the-shelf coding agents with only terminal access to the robot's native software interface ROS 2. OpenRUA employs a minimalist workspace-as-harness design, only offering ROS 2 documentation and basic tools while leaving the coding agent to organize its own work without orchestrating any agentic workflow. Within this workspace, OpenRUA recasts perception as file I/O and manipulation as coding. With Claude Code powered by Claude Opus 5, OpenRUA achieves success rates of 99.0% on CaP-Bench and 87.0% on LIBERO-PRO, demonstrating that an off-the-shelf coding agent can serve as a zero-shot visuomotor policy through the robot's native interface, without bespoke primitives or task-specific training. Under this minimalist design, further analysis reveals striking emergent behaviors of coding agents: (1) For perception, the agent spontaneously writes programs that process raw sensory inputs and derive metric measurements in 96.80% of episodes. (2) For manipulation, the agent spontaneously builds motion-control clients (e.g., gripper control) in 95.87% of episodes and closed-loop control programs (e.g., adjusting motion based on sensor feedback) in 50.13% of episodes. Our code is available at https://github.com/terminalworld/OpenRUA.

Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Because the value of each design choice is observable only through execution, tailoring a harness to each query has required either executing alternatives at inference time or costly manual design. We introduce SHIFT, which moves execution out of the per-query search loop. A local LLM architect learns a policy over harness-building actions from search, and a value function that predicts, from measured executions, a utility balancing accuracy against execution cost. For each query, Monte Carlo tree search uses these predictions to construct a harness. Across 9,193 tasks in six benchmarks, from math to document and general-assistant tasks, with a Gemini 3.5 Flash executor, SHIFT attains the highest mean accuracy, about 80%, outperforming 17 baselines that span prompting, prompt optimization, and workflow search, and exceeding the strongest baseline by 7.2 percentage points. A cheaper mode of SHIFT also attains a higher mean accuracy than every baseline while using 32% fewer execution tokens than the strongest baseline. We further show that choosing structure, instructions, and tools jointly beats choosing only instructions or only tools by up to 9.1 percentage points, and that learned value selection identifies more accurate harnesses with lower execution cost from candidate pools.

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among several agents, wired together by a harness: the program that fixes which roles exist, how they pass information, which tools each may call, and how retries are coordinated. When the language model is held fixed, changing only the harness can still change success rates by several-fold on public agent benchmarks, yet most harnesses are written by hand; recent harness optimizers each search only a narrow slice of the design space and rely on coarse pass/fail feedback that gives no diagnostic signal about why a trial failed. AgentFlow addresses both limitations with a typed graph DSL whose search space jointly covers agent roles, prompts, tools, communication topology, and coordination protocol, paired with a feedback-driven outer loop that reads runtime signals from the target program itself to diagnose which part of the harness caused the failure and rewrite it accordingly. We evaluate AgentFlow on TerminalBench-2 with Claude Opus 4.6 and on Google Chrome with Kimi K2.5. AgentFlow reaches 84.3% on TerminalBench-2, the highest score in the public leaderboard snapshot we evaluate against, and discovers ten previously unknown zero-day vulnerabilities in Google Chrome, including two Critical sandbox-escape vulnerabilities (CVE-2026-5280 and CVE-2026-6297).

As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. We introduce agentic meta-reasoning, an inference-time harness that makes these choices an explicit and structured reasoning process. Workers carry out the task-level computation, while a controller consolidates what the run has established, explores next options, assesses what each option is worth under the remaining budget, and dispatches the chosen work with context drawn from persistent memory. Between decisions the controller carries only a compact account of the run rather than replaying its full history. Our baselines span production coding agents and research harnesses, together with a Direct Control Agent using the same workers and compute budget allowance. On ProgramBench, which tests long-horizon agentic capability through program reconstruction, meta-reasoning achieves 71.5% with GPT-5.5 against 58.0% for Codex; with Opus 4.8 it achieves 67.2% against 65.5% for Claude Code. On the other benchmarks, spanning abstract reasoning, multi-domain long-horizon reasoning, and proof generation, it gains between 3.6 and 4.2 points over direct control, averaged across three frontier models. It keeps improving over the tested budget ranges where direct control plateaus, though its overhead can hurt at small budgets. Artifact-graph analysis reveals more reuse of earlier work, higher coverage of correct solutions in most settings, and nonuniform gains in final selection. These results indicate that spending computation on structured control becomes more important as agents scale to longer runs.

AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic Agent Leaderboard (HAL) to address these challenges. We make three main contributions. First, we provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of VMs, reducing evaluation time from weeks to hours while eliminating common implementation bugs. Second, we conduct three-dimensional analysis spanning models, scaffolds, and benchmarks. We validate the harness by conducting 21,730 agent rollouts across 9 models and 9 benchmarks in coding, web navigation, science, and customer service with a total cost of about $40,000. Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs. Third, we use LLM-aided log inspection to uncover previously unreported behaviors, such as searching for the benchmark on HuggingFace instead of solving a task, or misusing credit cards in flight booking tasks. We share all agent logs, comprising 2.5B tokens of language model calls, to incentivize further research into agent behavior. By standardizing how the field evaluates agents and addressing common pitfalls in agent evaluation, we hope to shift the focus from agents that ace benchmarks to agents that work reliably in the real world.

We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming subtle technical obstructions, and retaining intermediate progress over a long horizon. Cogentic addresses these challenges through an iterative prove-verify loop in which an orchestrator allocates a population of independent provers across distinct proof directions, subjects their output to adversarial verification by several specialized components, and promotes confirmed intermediate results into a persistent verified ledger that later rounds build on. The harness is designed to be able to solve research-level math and theoretical computer science problems. Using either Gemini 3.1 Pro or an early version of Gemini 4 Argon as the base model, Cogentic produced novel results on open problems across online learning, auction theory, and mechanism design. Each result was independently verified by domain experts and is developed in full in companion papers. We list these results, and new ones as they are verified, at https://sites.google.com/view/cogentic .

Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness updates can change which model capabilities are exposed. Existing joint-adaptation methods optimize weights and textual prompts but leave the broader harness fixed. We propose Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current harness, then searching for a better harness under the updated model. We instantiate these two phases with online rejection-sampling fine-tuning and Meta-Harness, respectively. When to switch is a key design choice: to separate real improvements from noise without over-optimizing against a changing counterpart, WHALE uses either fixed phase durations or an adaptive patience rule over training signals. Using Qwen3.5-2B/4B agents across three domains (search question answering, mathematical reasoning, and chess puzzles), WHALE outperforms weight-only, harness-only, and Fast-Slow Training by 4.15-24.38 percentage points in best mean@8 accuracy. Either component can be the bottleneck: harness search matches peak weight-only accuracy with far fewer rollouts in SearchQA, but improves math accuracy only after a weight update. Small interleaved updates also outperform stagewise weight-then-harness optimization in accuracy and rollout cost. The code is available at https://github.com/krafton-ai/WHALE.

This paper presents Safurai-001, a new Large Language Model (LLM) with significant potential in the domain of coding assistance. Driven by recent advancements in coding LLMs, Safurai-001 competes in performance with the latest models like WizardCoder [Xu et al., 2023], PanguCoder [Shen et al., 2023] and Phi-1 [Gunasekar et al., 2023] but aims to deliver a more conversational interaction. By capitalizing on the progress in data engineering (including latest techniques of data transformation and prompt engineering) and instruction tuning, this new model promises to stand toe-to-toe with recent closed and open source developments. Recognizing the need for an efficacious evaluation metric for coding LLMs, this paper also introduces GPT4-based MultiParameters, an evaluation benchmark that harnesses varied parameters to present a comprehensive insight into the models functioning and performance. Our assessment shows that Safurai-001 can outperform GPT-3.5 by 1.58% and WizardCoder by 18.78% in the Code Readability parameter and more.

Earth observation (EO) models are still built by hand. For each new task, experts design a training recipe and tune it against a benchmark. We show that this loop can be handed to an agent. Any verifiable task can be cast as a harness and a verifier, where the harness defines what the agent may use and the verifier defines what counts as success. Every EO task can be made verifiable, through labeled benchmarks, independent sensors, physical models or the repeated observation of the same place. Given only these two components, a general-purpose coding agent builds the EO model and improves it recursively on its own outputs. Settings long treated as separate research problems, from learning with a handful of labels to adapting across domains, become choices of harness and verifier. On four EO benchmarks spanning optical, SAR and multispectral time-series imagery, agent-built models surpass the state of the art and keep most of that accuracy from about 1% of the training labels. This establishes a new paradigm for EO, in which people design harnesses and verifiers and agents build the models, so EO models improve as agents do.

Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successes remain largely confined in digital environments. We conjecture that the missing abstraction to automate robotics research is a repeatable feedback loop for real-world policy improvement: reset the scene, execute a policy, verify the outcome, and refine the next iteration. To bridge this gap, we introduce ENPIRE, a harness framework for coding agents that instantiates this physical feedback routine with four core modules: an Environment module (EN) for automatic reset and verification, a Policy Improvement module (PI) that launches policy refinement, a Rollout module (R) to evaluate policies with one or multiple physical robots operating in parallel, and an Evolution module (E) in which coding agents analyze logs, consult literature, improve training infrastructure and algorithm code to address failure modes. This closed-loop system transforms real-world manipulation learning into a controllable optimization procedure, minimizing human effort while allowing fair ablations across training recipe and agent variants. Powered by ENPIRE, frontier coding agents can autonomously train a policy to achieve a 99% success rate on challenging, dexterous manipulation tasks, such as organizing a pin box, fastening a zip tie, and tool use, a process that further accelerates when we dispatch an agent team on a robot fleet. Our results suggest a practical and scalable path toward deploying coding agents to autonomously advancing robotics in the physical world.

Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents. This gap is reflected in their limited performance on continual learning benchmarks such as ARC-AGI-3, especially when models are evaluated out of the box. Various agent harnesses have been proposed to close this gap, and each commits to a strategy for handling long sequences of observations, i.e., what information to save from the environment and how to load it into model context, a choice we argue is particularly consequential. Existing methods for context management face a significant tradeoff, as preserving more information makes retrieving relevant details less tractable. We propose PRO-LONG, a minimal context management framework built around programmatic memory for LLM agents in long-horizon, exploratory settings. PRO-LONG addresses the tradeoff by keeping a complete, structured interaction log and capitalizing on recent progress in coding agents to search this history efficiently. On the full ARC-AGI-3 public game set, PRO-LONG improves over a base coding agent by an average of 18.0 percentage points across frontier models, and matches or exceeds state-of-the-art specialized harnesses (up to 76.1% pass@1) while using 4.2-5.8x fewer tokens. With Fable 5, PRO-LONG achieves 97.4% best@2 at a total cost of \$1,750. Relevant code and logs are available at https://github.com/alexisfox7/PRO-LONG.

Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore an interface, implement software, and run and visually verify their artifacts. We introduce RecreationWorld, a five-platform framework built around recreation: given a running reference, an agent must discover its behavior and build a faithful implementation with no prescribed workflow. RecreationWorld provides reproducible environments on Ubuntu, macOS, Windows, Android, and Web, plus a unified harness with native GUI control and coding tools. The running reference serves as an oracle for hidden behavioral tests, providing execution-grounded rewards. We scale trajectory generation with high-quality open-source applications. Models trained on these trajectories improve across five out-of-distribution coding and hybrid computer-use benchmarks and more frequently verify their rendered outputs, providing evidence of transfer beyond recreation. For held-out evaluation, we introduce RecreationBench, comprising 250 diverse tasks across domains and platforms. Reference-grounded programmatic and visual assertions cover action-conditioned outcomes at multiple interaction depths; each is validated on the reference and by human reviewers before the suite is frozen for automatic scoring. GPT-6 Astra leads at 58.1% overall, but passes all programmatic tests on just 2.8% of tasks. Agents reproduce static interface structure more reliably than interactions and computed outputs, while generated applications remain smaller and more monolithic than their references. We release the benchmark, environments, and test suites.

Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack surface. Existing studies have revealed unsafe agent behaviors induced by skill-based attacks, but they primarily evaluate poisoned skills within a single task execution and enumerate harms through ad-hoc risk lists. To bridge these gaps, we introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle, paired with a systematic taxonomy of skill-relevant risks. SkillHarm evaluates two attack scenarios: Fixed-Payload Poisoning (FPP), where a fixed poisoned skill package directly compromises any task session that invokes it, and Self-Mutating Poisoning (SMP), where an initially benign execution silently mutates persistent skill content, deferring harm until a subsequent reuse. It further defines 12 risk types based on the agent workflow component targeted by the harm: data pipelines, system environments, and agent autonomy. To instantiate these attacks at scale, we build AutoSkillHarm, an automated construction pipeline with coding agents driven by natural-language harnesses. The resulting benchmark contains 879 attack samples across 71 skills. Experiments show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP. Our analysis further reveals a latent risk: many apparent attack failures stem from the agent failing to engage with the poisoned file rather than genuine resistance, and current defenses still fail to reliably mitigate the threat.

Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for evaluation without human involvement. Despite their flexibility, their reliability on long tasks spanning multiple applications remains unclear. A trajectory, composed of long sequences of screenshots and actions, may appear complete, but in reality violates constraints from the instruction or introduces an unwanted side effect. To identify these errors, a judge needs to examine the trajectory with respect to the user's instruction. To this end, we introduce AgentHorizon, a benchmark of 1,373 computer-use tasks (instruction-trajectory pairs) drawn from 166 hours of human-recorded trajectories spanning three operating systems. By recording trajectories for closely related instructions, we can construct negative tasks by swapping the instructions. This paired design evaluates judges on their ability to distinguish a successful trajectory from one that completed a similar (but incompatible) request. We release the benchmark under three splits: a frontier split, AgentHorizon (AH), a simplified split, AgentHorizon-Simple (AH-S), and a development split, AgentHorizon-Development (AH-D). We further evaluate eleven judges by (1) directly passing the full trajectory (with up to 300 screenshots and actions), and (2) using them as coding agents across five agent harnesses. We find that our best agentic judge, GPT-5.5, achieves 80.9% balanced accuracy on the AH subset. We find that tool-use improves certain models but results in worse performance for open-weight models, and that judges differ drastically in their ability to accept a valid trajectory and reject failed ones. Our findings highlight the need for judges that are capable of locating and verifying often hidden evidence that a task was properly completed inside long interaction histories.

Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context. Productization adds requirements for source boundaries, entity routing, answer contracts, and reproducible traces. We present a harness-engineering approach that reconstructs this pattern into a traceable, auditable LLM-agent architecture: deterministic behavior moves into code, manifests, schemas, and validation artifacts around a replaceable composition boundary, while source-backed claims remain the authority for runtime answers. We instantiate it on a public-data slice of five Korean corporate groups (25 listed companies) and evaluate three research questions. (1) The harness preserves its source-grounding, entity-routing, trace, output-hygiene, and recommendation-language contracts across the fixed validation scenarios; a fault-injection control confirms the validators flag deliberately broken contracts. (2) The checks the harness enforces held under model substitution: across three hosted models, they passed on all 270 composition-boundary runs; failures were confined to the model-composed side and were caught and recorded. (3) The code-owned guarantees are load-bearing, not reproducible by prompting alone: holding the model fixed and varying only the enforcement layer, prompt instructions alone let recommendation-language and internal-trace-leakage violations reach the reader, which the harness blocks entirely. A bolt-on external guardrail prevents such violations too but over-refuses, dropping utility to 88/120 where the harness preserves full utility (120/120); in this ablation, only code-owned enforcement preserves both safety and utility. The result is a reusable engineering pattern for turning exploratory prototypes into auditable applications with versioned source, control, and validation artifacts.

AI systems for software development are rapidly gaining prominence, yet significant challenges remain in ensuring their safety. To address this, Amazon launched the Trusted AI track of the Amazon Nova AI Challenge, a global competition among 10 university teams to drive advances in secure AI. In the challenge, five teams focus on developing automated red teaming bots, while the other five create safe AI assistants. This challenge provides teams with a unique platform to evaluate automated red-teaming and safety alignment methods through head-to-head adversarial tournaments where red teams have multi-turn conversations with the competing AI coding assistants to test their safety alignment. Along with this, the challenge provides teams with a feed of high quality annotated data to fuel iterative improvement. Throughout the challenge, teams developed state-of-the-art techniques, introducing novel approaches in reasoning-based safety alignment, robust model guardrails, multi-turn jail-breaking, and efficient probing of large language models (LLMs). To support these efforts, the Amazon Nova AI Challenge team made substantial scientific and engineering investments, including building a custom baseline coding specialist model for the challenge from scratch, developing a tournament orchestration service, and creating an evaluation harness. This paper outlines the advancements made by university teams and the Amazon Nova AI Challenge team in addressing the safety challenges of AI for software development, highlighting this collaborative effort to raise the bar for AI safety.

LLM agents increasingly rely on agent harness: the runtime infrastructure around the base model that defines execution environments, tool interfaces, context, lifecycle orchestration, observability, verification, and governance. Existing self-improving agents and automatic harness evolution methods mainly improve agents through runtime supervision, prompt optimization, workflow search, or harness modification based on final outcomes. However, they often fail to diagnose where the responsible evidence lies in failed trajectories and which harness implementation mechanism causes the unreliable behavior, resulting in broad, indirect, or poorly scoped changes. This paper proposes HarnessFix, a trace-grounded and diagnosis-driven framework for repairing agent harnesses. HarnessFix compiles raw execution traces and harness artifacts into a Harness-aware Trace Intermediate Representation (HTIR), which normalizes fragmented trajectory evidence, captures step-level data-flow and control-flow relations, and aligns runtime steps with the harness artifacts that shape their behavior. It then attributes failures to responsible steps and harness artifacts, and consolidates recurring diagnoses into repair-oriented flaw records. Finally, HarnessFix maps these records to scoped repair operators, generates patches under flaw-specific repair specifications, and accepts them through regression-aware validation. We evaluate HarnessFix on four popular benchmarks, and results show that it improves the performance over the initial harnesses by 6.3% to 18.4%, significantly outperforming human-designed and self-evolution baselines. HarnessFix highlights the value of treating failed trajectories not only as feedback signals, but also as structured evidence for diagnosing and repairing the harness mechanisms behind agent failures.

Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on fixed offline benchmarks. Real deployments instead present open-ended task streams: histories grow without a fixed endpoint, heterogeneous tasks require different harnesses, and problem distributions shift over time. These challenges make a single repeatedly and densely updated harness brittle, causing performance degradation as accuracy peaks early and then declines. This motivates sustained harness construction with task-wise adaptation. We introduce Adaptive Auto-Harness, a framework and system for such streams. The framework decomposes the gap to an oracle harness into evolution loss and adaptation loss. The system addresses these losses with a stateful multi-agent evolver, a harness tree with solve-time routing, and human-steering hooks for cases where history lacks the needed signal. Across prediction-market, security-competition, and event-forecasting streams, Adaptive Auto-Harness outperforms five existing auto-harness baselines and ablations attribute gains to better construction, routing, or targeted human steering. Code is available in https://github.com/A-EVO-Lab/AdaptiveHarness .

We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness configurations and then report final performance on the same public benchmark. This protocol raises two fundamental concerns. First, harness evolution is itself an iterative search procedure that repeatedly evaluates and revises candidate harnesses using task feedback. As in agentic test-time scaling, it should therefore be compared with simple task-level search baselines under matched feedback and inference budgets to determine whether its gains arise from improved harness design or from additional search alone. Second, because the search and the final evaluation share the same benchmark, the reported gains risk overfitting to that specific task set. To address these concerns, we conduct an extensive evaluation comparing harness evolution with simple test-time scaling and discovery baselines under comparable feedback and inference budgets, and also evaluate evolved harnesses on held-out tasks to assess whether the discovered improvements generalize. Experiments on Terminal-Bench 2.1 with GPT-5.4 and Claude Opus 4.6 show that automatic harness evolution does not consistently outperform simple test-time scaling methods and exhibits limited generalization. Our results raise important questions about the effectiveness of automatic harness evolution and highlight the need for fairer evaluation protocols and benchmarks for automatic harness design. Our code is available at https://github.com/rethinking-harness-evolution.