Daily Papers

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it fails. We present VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations and a statically validated execution plan before any frame is observed. During execution, observations gate and scope only declared calls to frozen low-level experts (e.g., segmentation and tracking, counting, eleven typed physical measurements over the resulting tracks, depth, OCR, and audio-event detection). Each action returns a provenance-carrying evidence record whose payload, when usable, is either a typed measurement or an explicitly tagged learned state. Typed resolvers and fixed composition map usable records to a three-valued state (supported, contradicted, or unknown, surfaced as plausible, implausible, or abstain) with full provenance, so that every verdict is traceable to the evidence that produced it. We anchor evaluation in a 1,500-clip corpus of human-annotated flaw records that localize real generation failures in prompt reference, space, and time. On a 149-clip core carrying 304 such records, VeriPhy accounts for 228, against 164 for a published question-decomposition evaluator given the same clips and the same claims. Recall alone does not separate it from prompting the same backbone monolithically, which reaches 222; what separates them is that each decision retains its evidence record and provenance, making the traces auditable one verdict at a time and usable as the interface through which a critic verdict could be written back into generation.

Every production model is updated, by retraining, fine-tuning, quantization, or a silent vendor swap, and each update risks being worse than what it replaced. We formalize update promotion as certified paired risk-difference auditing. Our starting point is a support identity: the risk difference between two models lives on the inputs where they disagree, observable without labels. We build DISCERN, a sequential two-tier protocol. A zero-label tier certifies benign updates whose disagreement rate is below tolerance from unlabeled traffic alone. An audited tier labels only sampled disagreements through an anytime-valid confidence sequence, valid at every stopping time and under any label-routing rule, even an adversarial judge. We prove finite-sample validity and matching label-complexity bounds of order rho^2/eps^2 at the rate level, so exploiting free disagreement provably saves a factor 1/rho over any pairing-blind auditor, and the guarantee composes across an unbounded sequence of promotions from one error budget. Across 14,000+ replayed audit streams over 785 update pairs, including LoRA fine-tunes of language models up to 1.4B parameters, miscoverage is 0.0002 (nominal 5%), power 0.986 with zero false alarms, and 56% of benign updates certify with zero labels. Each audit emits a machine-checkable evidence record for post-market monitoring.

Explainable artificial intelligence (XAI) encompasses methods that draw on different sources of information and address different explanatory needs. A common framework is needed to describe how this information becomes evidence and is communicated as an explanation for a particular recipient. We propose the General Framework for Generating Explanations (GFGE), grounded in interpretative frameworks and the complementary activities of sense-reading and sense-giving. Its conceptual foundation is the Interpret/Explain Schema (IES), which connects an analyst's interpretation of system evidence, the communication of a selected account, and the recipient's interpretation of that account. GFGE operationalises this schema through five roles: data interpretation, model interpretation, output interpretation, optional post-hoc analysis, and aggregation. A role-typed operation graph records method-specific dependencies, while evidence records retain the sources, assumptions, and limitations of explanatory claims. The explanatory question, audience, and context guide the procedure. We instantiate GFGE for attribution, surrogate, counterfactual, concept and prototype, intrinsic rule, argumentation, and language-model methods. These instantiations show how intrinsic, post-hoc, and hybrid workflows can be represented through the same roles while preserving their distinct evidential requirements. GFGE provides a common basis for analysing explanation workflows, tracing communicated claims to their evidence, and identifying unresolved explanatory dependencies.

Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The challenge is to form reusable factual memory without compromising real-time perception. We introduce OneStreamer, which jointly learns query-independent evidence recording and task response through a shared proactive generation process. Its Proactive Hierarchical Caption Memory (PHCM) produces time-grounded local-detail captions and summaries of completed events. Streaming caption targets supervise the interpretation of observed video prefixes during training. At inference, model-generated records complement a recent visual window, providing reusable factual context without revisiting historical visual features. Proactive State Transition Learning (PSTL) reduces the dominance of repeated waiting states by preserving supervision at all output anchors and selecting representative state-change and state-persistence tokens. We further develop a streaming data synthesis pipeline that aligns output content and timing with available evidence. Combining the resulting streaming captions and QA with cleaned open-source data yields OneStreamer-1M, a broad-coverage streaming video interaction dataset with over one million records spanning diverse tasks. Our 4B model achieves the best results among the compared methods across all eight evaluated streaming video understanding benchmarks. Ablations show that retaining generated captions improves historical QA without degrading real-time perception. PSTL also outperforms dense state supervision while supervising only 27.5% of annotated state tokens. Together, these results support proactive generation as a shared learning interface connecting perception, memory formation, and timely response in streaming video interaction.

Scientific machine learning papers typically make computational claims, e.g., that the relative mean square error is less than 5% or that the 95% predictive credible interval covers the test data. A coding agent can be prompted to replicate those claims from paper materials alone, but the prompt does not by itself reliably preserve progress or check whether generated evidence supports the paper's claims. We introduce Paper-replication, a workflow that makes each selected paper claim a target with recorded evidence, and implement it as a coding-agent skill. The workflow makes the agent record those targets, reconstruct the paper's method, run computational experiments, link generated outputs to provenance and comparisons with the paper's claims, record where matched evidence appears in the replication report, and pass validation checks before completion. We evaluate Paper-replication on twelve independent runs across four scientific machine learning papers. All twelve workspaces pass the completion gate, and all 158 recorded targets are matched with report coverage. Even in this completed workspace state, repeated runs differ in how papers are divided into targets, in numerical fidelity to the source papers, in elapsed replication time, in the number of intermediate executions replaced before final evidence is accepted, and in the rules used to accept evidence. Paper-replication makes completion depend on workspace evidence and validation checks rather than on the agent's final message.

We introduce Forecast-Dojo, a replayable environment for benchmarking and training LLM forecasting agents. It combines resolved prediction-market questions with dated news, allowing agents to research an event and revisit their predictions at successive historical dates. The same tasks and tools support repeated evaluation, collection of training interactions, and feedback from recorded outcomes without waiting for new events to resolve. Forecast-Dojo contains 1,568 Polymarket events, split by time into training and evaluation periods, and 18.8M dated news articles. In an evaluation of 12 models, research tools lower Brier score for all 12. Forecasts also improve as events unfold, with the largest gains at steps where more newly dated evidence is recorded. Every model still trails historical market forecasts in both Brier score and accuracy. A belief notebook carried between dates lowers research cost but does not consistently improve forecast quality. Beyond evaluation, Forecast-Dojo provides interaction trajectories and outcome feedback for agent learning, with supervised fine-tuning as a proof of concept.

The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence over a movie corpus while an orchestrator holds the record and rules on what may be submitted. A claim is admitted only once an entailment cascade has checked it against the passage it cites, and an answer is released only once enough checked evidence stands behind it. Each question is run three or four times, every pass retrieving from a corpus stripped of what the earlier passes have already seen. The confidence filed with each answer is computed by the orchestrator from what the run leaves behind and is never asked of the model, which is offered no way to rate itself. The two retrieval runs placed 4th and 5th of 22, pooling the passes was worth 0.0709 nDCG@20, and the gain was largest on the multi-hop and post-processing-heavy questions, where the organisers rank the pooled run top of the field. Sixteen of the 25 answer runs were built on passages these two runs supplied, 12 of them filed by other teams. HMR rewards a system whose confidence is high where it answers right and low where it answers wrong. The pipeline reached an accuracy of 0.9219, 6th of 25, while the confidence filed with those answers gave an HMR of 0.4915, 13th. A few rules crafted over those same recorded signals, with no further model call and no further retrieval, raise that to an accuracy of 0.9375, 5th, and an HMR of 0.6985, 9th. Ranking on HMR alone can reward a system for answering wrongly with low confidence, so we propose accHMR, the accuracy multiplied by HMR, which reports the reward in proportion to the accuracy, and on which the revised rules would have scored 0.6549, 5th. For future work, fitting a model on the numbers the pipeline already produces, rather than writing such rules by hand, would be a real step forward.

Modern agent systems often suffer from fragmented runtime state: transcripts, tool effects, memory events, workspace placement, branch provenance, and replay evidence are recorded separately and become difficult to inspect or reproduce. OpenRath addresses this issue with a PyTorch-like programming model for multi-agent, multi-session systems. The analogy concerns the role of a central first-class runtime abstraction, not tensor computation. Its core abstraction is Session, the runtime value passed between agents and workflows. A Session is branchable, inspectable, replayable, backend-aware, and composable. It records conversation chunks, sandbox placement, lineage metadata, token usage, pending work, and tool evidence, while defining where memory interactions enter the runtime record. Since this state is carried by the same value used in program execution, fork, merge, and replay become explicit runtime operations rather than states reconstructed from external traces. OpenRath further defines Sandbox, Tool, Agent, Memory, Workflow, and Selector, with Selector turning control flow into runtime-routed decisions. This report presents the programming model, architecture, audited milestones, and evidence protocol. Its claims are limited to controlled runtime properties, while broad quantitative comparisons, live-provider quality, optional-backend availability, and memory quality are left for follow-on evaluation. The central thesis is that Session provides agent systems with a first-class runtime value for auditable composition.

A companion that talks with a person for months should come to understand them. It should remember what they said, infer who they are, and know when the past bears on the message in front of it. Testing this requires a real person's record, and such records are private, so benchmarks generate the person and the questions and settle in advance what matters. We release \bench, ten real relationships with an AI companion: 27,218 messages over up to 120 days, released as the conversation and four files derived from it, a profile, a persona, a chat ground truth and a question set, each citing the messages it rests on. Every chat label carries the reasoning trace that produced it, checked stage by stage against the conversation. Three findings follow. First, the past is rarely needed and far away. Pooled measures mislead: a recency window finds the required message for 95.9\% of probes and 2.2\% of those that need memory, and at the natural rate 96\% of the gain from supplying recorded evidence comes from messages that need none. Second, no detector we tried can tell when memory is needed on real messages, authored questions over the same histories leak the cue, and labeling the same messages as memories raises their use by ten to fourteen points. Third, three agent systems reconstruct the persona with the same F1 at a 31-fold difference in cost.

Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy multimodal observations accumulate in conversation history and disrupt later decisions, while multimodal models have limited capacity for multi-step planning. Controlled backend replacements support this diagnosis: replacing the planner causes a much larger performance loss than replacing the perception backend. We present Omni-Decision, an omni-modal agent built on evidence-ledger planning: it replaces the growing dialogue history with an explicit evidence ledger that records what evidence is still missing, what has been confirmed, and where records conflict. A critic reads each noisy observation and passes only the usable content to the ledger, discarding the rest, so the planner works from a compact context throughout the task. Each run records the state, action, and verdict at every step, and supervised fine-tuning and decision-level reinforcement learning on these trajectories further improve the planner. Omni-Decision achieves state-of-the-art accuracy of 81.4% on OmniGAIA at approximately 43% of Gemini-3.1-Pro's cost per question, and 65.0% on WorldSense long-video understanding, level with the strongest end-to-end model.

Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent. This makes retrieval failures more specific than broad irrelevance. A system can find the right capability family yet expose the wrong same-capability representative. We study this failure as same-capability risk-exposure retrieval. Each benchmark unit pairs a helpful skill with a query-specific risky sibling that shares the capability family but differs on an execution-controlling contract, such as the required resource, precondition, procedure, or artifact. We introduce SameCapRisk-Bench, an auditable benchmark with 1,190 skill-risk units and 1,686 evaluation query cases: 694 marked-sibling units under public library pressure and 496 hard role-flip units where the same two skills swap helpful/risky roles across paired queries. The release records admission evidence, cue/leakage checks, source hashes, family relations, and fixed candidate pools. The benchmark reports helpful ranking together with harmful sibling rate (HSR@K), the top-K exposure of the marked risky sibling. On this benchmark, public SkillRouter, SkillRet, and R3-Skill retrieve helpful skills at high Recall@3 (0.848--0.888) but also expose marked risky siblings frequently (HSR@3 0.346--0.372). A fully public score-and-cluster pipeline lowers HSR@3 to 0.128--0.182, with Recall@3 of 0.713--0.776. Under a benchmark-trained reference scorer, public text-cluster and controlled resolvers reach HSR@3 0.012 and 0.007; the latter attains Recall@3 0.833. Skill retrieval should therefore report both capability matching and same-family risk exposure, with HSR serving as a targeted exposure certificate for fixed skill libraries.

Retrieval-augmented generation (RAG) enables agents to access external knowledge at inference time, but it primarily retrieves fragmented declarative evidence, leaving agents to repeatedly infer task procedures from passages, manuals, examples, logs, or trajectories. This raises a fundamental question: can skills extracted from external knowledge bases be installed into an agent, enabling it to rapidly approximate domain expertise? In this paper, we propose Anything2Skill, a taxonomy-guided framework that compiles heterogeneous external knowledge into reusable, retrievable, and executable skills for agents. Given a corpus of knowledge records, Anything2Skill first decomposes each record into evidence windows and performs plan-and-expand skill extraction under a skill-tree prior. The extracted candidates are then converted into structured skill contracts that specify invocation conditions, contraindications, action moves, workflow steps, constraints, output specifications, supporting evidence, and confidence scores. To construct a deployable procedural memory, Anything2Skill manages the extracted skills in a persistent SkillBank through taxonomy-aware compilation, registry-level reconciliation, lifecycle tracking, versioned updates, and visible skill-tree projection. At inference time, agents retrieve both task-specific passages from the original knowledge base and relevant procedural skills from the SkillBank, allowing RAG to provide declarative evidence while compiled skills provide reusable procedural guidance. Experiments on qsv and GitHub-CLI show that Anything2Skill combined with RAG achieves 98.85\% and 94.10\% success rates, respectively, substantially outperforming RAG-only agents. These results suggest that compiling latent procedural knowledge into explicit skills is an effective way to extend retrieval-augmented agents from knowledge access toward capability reuse.

Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final output. We introduce SearchOS, a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state. First, we formulate open-domain information seeking as relational schema completion with grounded citations, where agents discover entities, populate attributes across linked tables, and anchor each value to source evidence. Then we design Search-Oriented Context Management (SOCM), which externalizes the evolving state into Frontier Task, an Evidence Graph, a Coverage Map, and Failure Memory. Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents and continuously refills freed slots with tasks targeting unresolved coverage gaps to improve utilization and throughput. To schedule and control the execution of search agents, SearchOS introduces a Search Tool Middleware Harness that intercepts model and tool interactions to record grounded evidence and react to stalls or budget exhaustion, and provides a reusable hierarchical skill system comprising strategy and access skills to augment the agents' search process and avoid repeating failed search patterns across runs. On WideSearch and GISA, SearchOS leads all metrics among the evaluated single- and multi-agent baselines, paving the way toward robust information-seeking collaboration.

Speech deepfake detectors usually emit one score per utterance, but a borderline score does not reveal why two examples differ during retrospective error analysis. We ask whether a final score can be calibrated from component fields while keeping those fields visible for inspection. We build a decision record with a passive detector score and a score from a probe applied to a marked copy. It also includes retrieval support held out of the evaluated family, a margin from a support-set profile, and raw neighbor closeness. A cross-fit calibrator combines these fields and two differences between raw scores into one final score. On matched ASVspoof development data, the calibrated record reduces equal error rate (EER) by 3.48 percentage points relative to the fixed retrieval-augmented rule. It reaches 8.43% EER, whereas a passive WavLM baseline reaches 6.71% on the same subset. The record is therefore not the strongest detector in this comparison. Its value is to retain inspectable component fields while producing one scalar score for retrospective diagnosis.

Third-party LLM gateways have become a critical infrastructure layer between applications and external LLM providers. Conventional gateways do more than forward traffic: they decide which provider and model are called, whether fallback occurred, which stream is delivered, and what usage record should be billed. Because these decisions and records are authored inside the operator-controlled service, clients cannot independently distinguish honest mediation from route substitution, hidden fallback, stream manipulation, or forged provenance. We present an evidence-bound LLM gateway architecture that separates the operator control plane from an attested execution plane. Within the gateway, a measured Attested Gateway Runtime (AGR) is the only component allowed to decrypt requests, enforce path policy, construct upstream calls, and sign evidence. Clients verify signed release metadata and fresh attestation before encrypting requests to keys bound to the AGR measurement. AGR enforces request-scoped routing, fallback, and endpoint constraints, invokes admitted providers, returns encrypted response streams, and signs evidence binding the policy, selected route, endpoint identity, stream commitments, and completion metadata to the attested runtime. An initial Rust prototype on AWS Nitro Enclaves shows modest mechanism overhead and fail-closed detection of policy, routing, endpoint, and stream-evidence tampering outside the attested runtime.

Many modern AI question-answering systems convert text into vectors and retrieve the closest matches to a user question. While effective for topical similarity, similarity scores alone do not explain why some retrieved text can serve as evidence while other equally similar text cannot. When many candidates receive similar scores, systems may select sentences that are redundant, incomplete, or address different conditions than the question requires. This paper presents a deterministic evidence selection framework for retrieval-augmented question answering. The approach introduces Meaning-Utility Estimation (MUE) and Diversity-Utility Estimation (DUE), fixed scoring and redundancy-control procedures that determine evidence admissibility prior to answer generation. Each sentence or record is evaluated independently using explicit signals for semantic relatedness, term coverage, conceptual distinctiveness, and redundancy. No training or fine-tuning is required. In the prototype, a unit is accepted only if it explicitly states the fact, rule, or condition required by the task. Units are not merged or expanded. If no unit independently satisfies the requirement, the system returns no answer. This deterministic gating produces compact, auditable evidence sets and establishes a clear boundary between relevant text and usable evidence.

While there are abundant researches about evaluating ChatGPT on natural language understanding and generation tasks, few studies have investigated how ChatGPT's behavior changes over time. In this paper, we collect a coarse-to-fine temporal dataset called ChatLog, consisting of two parts that update monthly and daily: ChatLog-Monthly is a dataset of 38,730 question-answer pairs collected every month including questions from both the reasoning and classification tasks. ChatLog-Daily, on the other hand, consists of ChatGPT's responses to 1000 identical questions for long-form generation every day. We conduct comprehensive automatic and human evaluation to provide the evidence for the existence of ChatGPT evolving patterns. We further analyze the unchanged characteristics of ChatGPT over time by extracting its knowledge and linguistic features. We find some stable features to improve the robustness of a RoBERTa-based detector on new versions of ChatGPT. We will continuously maintain our project at https://github.com/THU-KEG/ChatLog.

Musculoskeletal diseases are among the leading causes of disability worldwide and create the greatest global need for rehabilitation. Because recovery, remodelling and degeneration often unfold over months to years, musculoskeletal care requires longitudinal management that repeatedly integrates evolving patient evidence, external medical knowledge and stage-specific functional goals. In routine practice, this evidence is fragmented across visits, departments and hospital systems, limiting individualized, evidence-based care. Here we report OrthoPilot, a clinical artificial intelligence system powered by a large language model that integrates hospital data streams with authoritative external knowledge for continuous musculoskeletal management. OrthoPilot autonomously retrieves real-time imaging, laboratory, pathology and order data and converts evolving patient states into evidence-based decisions from admission diagnosis to rehabilitation planning. We established a specialist-validated benchmark from real-world electronic health records spanning 1,000 disease codes. In a reader study across the complete care pathway, OrthoPilot was compared with 81 orthopaedic physicians and surpassed experts with 25 years of experience in diagnostic reasoning, clinical decision-making and management planning. It also outperformed all evaluated intelligent systems across 60 external clinical centres. In a prospective study of 1,870 complex cases, OrthoPilot increased full-chain management success by 10.6%. During an 8-month randomised deployment involving 8,240 inpatients, it increased cumulative cases per bed by 9.7% and improved patient-reported access to health information. These results move clinical AI from predicting isolated events toward executing longitudinal management across complete musculoskeletal care pathways.

A growing literature argues that progress in human longevity is slowing, and that this slowdown may signal an approaching biological limit to lifespan. The argument rests on visible flattening of cumulative life expectancy records, evaluated through linear regressions or through comparisons of average gains across decades. These summaries, however, provide only weak evidence for slowing improvements, because they cannot distinguish a true from an apparent slowdown. An apparent slowdown may arise due to periods of low variance around unchanged mean annual gains. Applying a Bayesian change-point framework to annual gains, both at the best-practice frontier and separately for each record-holding country, we find no evidence that the expected annual gain has changed across nearly two centuries, but strong evidence that its variance has moved through distinct historical regimes, with progress most regular in recent decades. The recent flattening is consistent with a low-variance regime and provides little evidence for a decline in the underlying mean pace of improvement. Claims that the best-practice frontier signals a biological ceiling should therefore not rest on the recent bend in the cumulative record alone. The frontier is better read as an empirical benchmark, the highest country-specific survival achieved under observed historical conditions.

Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression severely dilutes fine-grained acoustic and visual evidence. We introduce LEAP, a framework where the model retrieves its own evidence without placing the whole recording in one context. LEAP divides a recording into fixed-duration blocks, applying a lightweight localization pass to each block to score short candidate windows. The highest-ranked windows are pooled and re-encoded in a single bounded answer pass. Consequently, the answer input and peak context remain independent of the recording duration. By decoupling evidence localization from reasoning, our framework can localize candidate temporal windows over pre-computed transcripts without decoding media frames, while preserving fine-grained visual and non-speech evidence by routing the final answering pass over raw audio-visual streams. LEAP trains both stages: a localization LoRA improves the selected windows, and an answer LoRA improves the answers read from the same windows. The block grid natively supports causal queries, enabling LEAP to support streaming inference without streaming-specific training. Across several AVQA benchmarks, LEAP improves over the Qwen3-Omni-30B-A3B baseline by 4.5-16.8%, and transfers to a second omni-modal backbone, MiniCPM-o 4.5, surpassing its published results by 3.1-13.0%.

Even though machine learning (ML) pipelines affect an increasing array of stakeholders, there is little work on how input from stakeholders is recorded and incorporated. We propose FeedbackLogs, addenda to existing documentation of ML pipelines, to track the input of multiple stakeholders. Each log records important details about the feedback collection process, the feedback itself, and how the feedback is used to update the ML pipeline. In this paper, we introduce and formalise a process for collecting a FeedbackLog. We also provide concrete use cases where FeedbackLogs can be employed as evidence for algorithmic auditing and as a tool to record updates based on stakeholder feedback.

AI-assisted research compresses ideation, implementation, evaluation, and manuscript writing into a single interactive loop. This compression is useful, but it also creates a publication risk: paper claims can become easier to state than to audit. We present ResearchLoop, an evidence-gated control plane for AI-assisted computational research. ResearchLoop treats research questions, task contracts, evidence objects, claim ledgers, closeouts, and paper bindings as durable project state, realized here as a repository-backed runtime. This technical report provides the complete protocol specification, state model, transition rules, claim-admission algorithm, and insight-compounding mechanism. It also reports the full experimental record spanning nine versions (V0--V9), including a self-hosting case study, a controlled task-suite study with component ablations, a mathematical olympiad evaluation, and a supplementary SciCode boundary experiment evaluated with the official generated-code harness. All artifacts, manifests, and verification reports are preserved in the project repository.

Visual retrieval-augmented generation (VRAG) augments vision-language models (VLMs) with external visual knowledge to ground reasoning and reduce hallucinations. Yet current VRAG systems often fail to reliably perceive and integrate evidence across multiple images, leading to weak grounding and erroneous conclusions. In this paper, we propose EVisRAG, an end-to-end framework that learns to reason with evidence-guided multi-image to address this issue. The model first observes retrieved images and records per-image evidence, then derives the final answer from the aggregated evidence. To train EVisRAG effectively, we introduce Reward-Scoped Group Relative Policy Optimization (RS-GRPO), which binds fine-grained rewards to scope-specific tokens to jointly optimize visual perception and reasoning abilities of VLMs. Experimental results on multiple visual question answering benchmarks demonstrate that EVisRAG delivers substantial end-to-end gains over backbone VLM with 27\% improvements on average. Further analysis shows that, powered by RS-GRPO, EVisRAG improves answer accuracy by precisely perceiving and localizing question-relevant evidence across multiple images and deriving the final answer from that evidence, much like a real detective.

We report three searches for high energy neutrino emission from astrophysical objects using data recorded with IceCube between 2011 and 2020. Improvements over previous work include new neutrino reconstruction and data calibration methods. In one search, the positions of 110 a priori selected gamma-ray sources were analyzed individually for a possible surplus of neutrinos over atmospheric and cosmic background expectations. We found an excess of 79_{-20}^{+22} neutrinos associated with the nearby active galaxy NGC 1068 at a significance of 4.2,σ. The excess, which is spatially consistent with the direction of the strongest clustering of neutrinos in the Northern Sky, is interpreted as direct evidence of TeV neutrino emission from a nearby active galaxy. The inferred flux exceeds the potential TeV gamma-ray flux by at least one order of magnitude.

Automated decision systems produce operational data across multiple infrastructure layers, yet no single logging format captures the complete governance-relevant record of how a decision was reached. Regulatory frameworks prescribe what must be recorded without specifying a data model for how to record it -- a gap this paper terms the Fragmented Trace Problem. Following a design science methodology, the paper presents the Decision Event Schema (DES), a JSON Schema specification that bridges four infrastructure layers -- ML inference, rule/policy evaluation, cross-system coupling, and governance metadata -- within a single per-decision event structure. The schema employs degradation-aware field design: each of six top-level field groups maps to a governance evidence property and the degradation type it must resist. DES defines ten required root-level fields and introduces a tiered evidence strategy (lightweight, sampled, full) that enables organizations to match evidence completeness to decision risk and throughput. A mechanism feasibility analysis demonstrates compatibility with the highest-throughput integrity mechanisms at production-scale decision rates. Evaluation against 25+ existing formats confirms that DES is the only specification covering all four layers simultaneously. The schema offers practitioners a reference adoptable directly or adaptable through namespace extensions, and regulators a mapping from requirements to minimum evidence tiers.

Runtime-governance evidence often collapses materially different events into one audit record: a decision may be made, an instruction dispatched or received, an action may or may not execute, and a resulting state may or may not be observed. This paper presents AIREP, a vendor- and model-independent protocol for per-decision AI runtime evidence. Its current wire model separates evidence into four artifact families: Decision, Control, Execution, and Effect. Artifacts use closed core schemas, explicit identities and digests, declared scope limits, RFC 8785 canonical JSON, domain-separated SHA-256 hashing, and pure Ed25519 signatures. A three-level assurance model distinguishes structural/hash consistency (AIREP-Core), verifier-accepted authorship (AIREP-Authenticated), and independently anchored chain-head freshness and non-truncation relative to an accepted witness (AIREP-Witnessed); these classes do not establish event truth. A structured reconciler preserves failure, missing evidence, unevaluated prerequisites, and indeterminate outcomes as distinct states. The released beta includes a four-family first-party producer, Python and Node reference-verification paths, adversarial/lifecycle corpora, and reproducible validation. Post-release first-party Hermes and LightEval integration exercises preserve explicit evidence boundaries without claiming adoption or interoperability. Independent implementation evidence exists separately for a v0.1.2 producer and a v0.2 consumer/verifier; because they target different frozen versions, they do not establish same-version producer-to-consumer interoperability. AIREP remains experimental.

Planning records define restrictions over geographic areas, but their source documents often provide only indirect spatial evidence rather than machine-readable boundaries. We introduce Plan2Map, a 208-case multimodal benchmark for document-grounded geospatial boundary reconstruction from UK planning records. Given only a source planning document, systems must reconstruct a valid geospatial boundary from notice text, schedules, map plates, map labels, and boundary annotations; the reference GeoJSON is held out for scoring. We propose GeoPlanAgent, a document-grounded, geospatial-tool-in-the-loop system that decomposes the task into evidence extraction, localisation, map registration, boundary segmentation, projection, and verification. On Plan2Map, GeoPlanAgent achieves 0.736 mean IoU and 0.904 median IoU, with 67.8\% of predictions at or above 0.8 IoU, substantially outperforming direct VLM-to-GeoJSON baselines. Diagnostic analysis shows that direct VLM prediction remains unreliable, while remaining errors are concentrated in localisation and map registration, and supervised boundary segmentation substantially improves pixel-level mask quality. Plan2Map provides a concrete testbed for multimodal geospatial reconstruction from public planning records. Project page: https://odeb1.github.io/Plan2Map_Project_Page/.

Clinical diagnosis at hospital admission must be made rapidly from limited, incomplete evidence. Existing diagnosis-prediction benchmarks are poorly suited to this setting: they restrict prediction to closed code sets, exclude free-text notes, and supervise with discharge diagnoses that incorporate the full inpatient course. We introduce EarlyDx, a large-scale benchmark for open-ended early diagnosis, built from 154,834 emergency department encounters in MIMIC-IV. Each encounter is restricted to records available at admission time t_0 and supervised by the diagnoses recorded during the ED encounter rather than at discharge. An LLM auditor further verifies every free-text label as supported, partially supported, or unsupported by that evidence; the primary evaluation scores only fully supported labels. Under a semantic LLM-as-judge protocol, no evaluated system --- frontier general, medical-specialized, or in-domain post-trained --- synthesizes admission-time evidence reliably. Zero-shot models score largely by extraction, recovering only 3-31% of diagnoses that must be inferred rather than read from the record; post-training raises inference-dependent recall to 56%, but a sizeable margin remains, and on time-critical conditions no system attains a clinician's balance of sensitivity and precision. We release the full construction and evaluation pipeline at here.

Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts, graphs or typed memories at write time. We argue that the work of memory divides, as thinking does, into two systems. Most of it is fast System 1 work: many small, independent yes/no judgments about records, such as whether a record is needed or no longer current, which a decision model makes by the dozen in a third of a second. Only a little is slow System 2 work: writing a few search queries, naming what the reply needs and composing the answer, which an LLM does well but slowly. We present Mnemon, a memory agent built on this division. It keeps conversations as raw, dated records; an LLM (System 2) plans searches over them, a decision model, Jev (System 1), judges what the searches return, and rules with explicit budgets turn the judgments into a small View for an unchanged answering model. A background pass consolidates each record once into topic timelines, value histories and standing instructions linked to the records, so that questions about a whole conversation reach evidence their own searches miss. Because nothing is decided about a record when it is written, the same agent can read any store that returns dated records. With gpt-4.1-mini answering, as in a public re-evaluation of 14 systems, Mnemon scores 91.7% on LoCoMo, the highest among them, and 83.8% on LongMemEval-S, from under 4k tokens of context per question, with the lowest effective cost index on LoCoMo. With a reasoning model answering, it reaches 92.2% on LoCoMo and 94.4% on LongMemEval-S, the latter on par with the best published results. From 100K to 10M tokens of history on BEAM, its cost per question grows by a factor of 1.11. On the same records, Jev separates gold evidence better than two LLMs and is 3-11 times faster.

Routine complete blood counts (CBCs) could yield new biomarkers, but the private records needed to evaluate candidates cannot be shared with frontier language model agents that excel at discovery. We distilled the evidence held in the Clalit Health Services panel of over 5.4 million patients into a released scoring tool: for each of 13 immune-mediated diseases, a graph attention network was trained inside the data boundary to predict the case-control AUC of candidate CBC expressions, and only the trained weights were released. The tool grounds an agent's propose-score-refine loop in real-world data without exposing any patient data. In external validation, agent-discovered expressions improved on their literature-seeded starting points by a median of 4.18 AUC percentage points, and across three independent cohorts, reranking the candidates of three frontier research tools improved on their first choices in most comparisons, with gains that varied by cohort. The released scorer supports privacy-preserving biomarker hypothesis generation.

Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected evidence rather than the ability to seek it across clinical records and longitudinal imaging. We propose CASE: a series of role-specific Clinical Agents for Seeking Evidence, together with a tool-use harness and an agentic post-training framework for compact vision-language policy models. We further introduce a longitudinal multimodal benchmark built on UK Biobank, comprising 50,401 clinical questions derived from real-world ICD-10-coded diagnoses of 4,739 participants. Each question links to a patient-specific environment containing clinical context and multi-sequence MRI from baseline and follow-up visits, where agents autonomously select which visits, organs, modalities, slices, and specialist tools to inspect and compare. Supervised fine-tuning transfers evidence-seeking workflows from 14,734 frontier-model interaction trajectories, followed by agentic reinforcement learning on the learner's own environment interactions. Privileged on-policy self-distillation and rubric-based LLM feedback refine evidence-to-conclusion reasoning without prescribing tool sequences. Experiments show that CASE moves beyond question-answer imitation toward transferable investigation policies, strengthening evidence-grounded longitudinal reasoning. Under matched evaluation conditions, our Qwen3-VL-8B based agent achieves over 16% and 10% relative improvements in answer accuracy over GPT-5.4 and Claude Opus 4.8. Code will be available at https://github.com/VinyehShaw/CASE.

An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from what they do. We compare stopping at the same step after longer and shorter runs of results the agent judged useless; this contrast is zero for clock- or deadline-driven stopping. Where we record their judgments, the seven agents we test call a failing source's results useless 97-100% of the time, yet most of them rarely stop on that judgment. Prompt cues change when they stop but not what they stop on. Permission to answer from memory and a reasoning mode can bring early stops regardless of evidence, a stated budget moves the 7-8B models' stops to the deadline, and a stopping rule or call cost in the prompt is followed at most partly. Stopping follows the evidence only when the harness enforces an integration step that makes the agent answer after five consecutive results it judged useless. This step raises failing-source success for every model, keeps the stopping point fixed when the budget doubles, and needs no extra judgment call when the agent states its judgments. A pre-registered replication on 300 fresh questions confirms the dissociation and the rule's effect.

Social determinants of health (SDoH) have an important impact on patient outcomes but are incompletely collected from the electronic health records (EHR). This study researched the ability of large language models to extract SDoH from free text in EHRs, where they are most commonly documented, and explored the role of synthetic clinical text for improving the extraction of these scarcely documented, yet extremely valuable, clinical data. 800 patient notes were annotated for SDoH categories, and several transformer-based models were evaluated. The study also experimented with synthetic data generation and assessed for algorithmic bias. Our best-performing models were fine-tuned Flan-T5 XL (macro-F1 0.71) for any SDoH, and Flan-T5 XXL (macro-F1 0.70). The benefit of augmenting fine-tuning with synthetic data varied across model architecture and size, with smaller Flan-T5 models (base and large) showing the greatest improvements in performance (delta F1 +0.12 to +0.23). Model performance was similar on the in-hospital system dataset but worse on the MIMIC-III dataset. Our best-performing fine-tuned models outperformed zero- and few-shot performance of ChatGPT-family models for both tasks. These fine-tuned models were less likely than ChatGPT to change their prediction when race/ethnicity and gender descriptors were added to the text, suggesting less algorithmic bias (p<0.05). At the patient-level, our models identified 93.8% of patients with adverse SDoH, while ICD-10 codes captured 2.0%. Our method can effectively extracted SDoH information from clinic notes, performing better compare to GPT zero- and few-shot settings. These models could enhance real-world evidence on SDoH and aid in identifying patients needing social support.

The solar wind is a medium characterized by strong turbulence and significant field fluctuations on various scales. Recent observations have revealed that magnetic turbulence exhibits a self-similar behavior. Similarly, high-resolution measurements of the proton density have shown comparable characteristics, prompting several studies into the multifractal properties of these density fluctuations. In this work, we show that low-resolution observations of the solar wind proton density over time, recorded by various spacecraft at Lagrange point L1, also exhibit non-linear and multifractal structures. The novelty of our study lies in the fact that this is the first systematic analysis of solar wind proton density using low-resolution (hourly) data collected by multiple spacecraft at the L1 Lagrange point over a span of 17 years. Furthermore, we interpret our results within the framework of non-extensive statistical mechanics, which appears to be consistent with the observed nonlinear behavior. Based on the data, we successfully validate the q-triplet predicted by non-extensive statistical theory. To the best of our knowledge, this represents the most rigorous and systematic validation to date of the q-triplet in the solar wind.

Multi-turn, multi-audio temporal question answering requires models to track target events across follow-up questions, recording switches, and historical references, recovering complete instances and their boundaries for temporal calculation and comparison. We propose TEMA, which connects event perception with evidence-based answering through Route, specifying the audio scope, and Span, describing all relevant intervals as conditional audio captions. We construct TEMA-Dialog with 40,704 dialogs and per-turn evidence and answer supervision, and TEMA-Bench for joint evaluation of evidence and final answers. Training combines temporal grounding initialization, full-dialog supervised fine-tuning, and completeness-first Span-only GRPO. Experiments on Qwen2.5-Omni and AF-Next show improved temporal question answering, particularly event localization and cross-audio comparison. Reinforcement learning applied solely to evidence further improves interval recovery and answer accuracy.

Large language model (LLM) systems are increasingly used to support high-stakes decision-making, but they typically perform worse when the available evidence is internally inconsistent. Such a scenario exists in real-world healthcare settings, with patient-reported symptoms contradicting medical signs. To study this problem, we introduce MIMIC-DOS, a dataset for short-horizon organ dysfunction worsening prediction in the intensive care unit (ICU) setting. We derive this dataset from the widely recognized MIMIC-IV, a publicly available electronic health record dataset, and construct it exclusively from cases in which discordance between signs and symptoms exists. This setting poses a substantial challenge for existing LLM-based approaches, with single-pass LLMs and agentic pipelines often struggling to reconcile such conflicting signals. To address this problem, we propose CARE: a multi-stage privacy-compliant agentic reasoning framework in which a remote LLM provides guidance by generating structured categories and transitions without accessing sensitive patient data, while a local LLM uses these categories and transitions to support evidence acquisition and final decision-making. Empirically, CARE achieves stronger performance across all key metrics compared to multiple baseline settings, showing that CARE can more robustly handle conflicting clinical evidence while preserving privacy.

Disease risk prediction has attracted increasing attention in the field of modern healthcare, especially with the latest advances in artificial intelligence (AI). Electronic health records (EHRs), which contain heterogeneous patient information, are widely used in disease risk prediction tasks. One challenge of applying AI models for risk prediction lies in generating interpretable evidence to support the prediction results while retaining the prediction ability. In order to address this problem, we propose the method of jointly embedding words and labels whereby attention modules learn the weights of words from medical notes according to their relevance to the names of risk prediction labels. This approach boosts interpretability by employing an attention mechanism and including the names of prediction tasks in the model. However, its application is only limited to the handling of textual inputs such as medical notes. In this paper, we propose a label dependent attention model LDAM to 1) improve the interpretability by exploiting Clinical-BERT (a biomedical language model pre-trained on a large clinical corpus) to encode biomedically meaningful features and labels jointly; 2) extend the idea of joint embedding to the processing of time-series data, and develop a multi-modal learning framework for integrating heterogeneous information from medical notes and time-series health status indicators. To demonstrate our method, we apply LDAM to the MIMIC-III dataset to predict different disease risks. We evaluate our method both quantitatively and qualitatively. Specifically, the predictive power of LDAM will be shown, and case studies will be carried out to illustrate its interpretability.

One important challenge of applying deep learning to electronic health records (EHR) is the complexity of their multimodal structure. EHR usually contains a mixture of structured (codes) and unstructured (free-text) data with sparse and irregular longitudinal features -- all of which doctors utilize when making decisions. In the deep learning regime, determining how different modality representations should be fused together is a difficult problem, which is often addressed by handcrafted modeling and intuition. In this work, we extend state-of-the-art neural architecture search (NAS) methods and propose MUltimodal Fusion Architecture SeArch (MUFASA) to simultaneously search across multimodal fusion strategies and modality-specific architectures for the first time. We demonstrate empirically that our MUFASA method outperforms established unimodal NAS on public EHR data with comparable computation costs. In addition, MUFASA produces architectures that outperform Transformer and Evolved Transformer. Compared with these baselines on CCS diagnosis code prediction, our discovered models improve top-5 recall from 0.88 to 0.91 and demonstrate the ability to generalize to other EHR tasks. Studying our top architecture in depth, we provide empirical evidence that MUFASA's improvements are derived from its ability to both customize modeling for each data modality and find effective fusion strategies.

Multi-hop question answering in retrieval-augmented gener?ation (RAG) often benefits from retrieving beyond the few candidates that will finally be read: narrow retrieval can miss an indispensable hop, while expanded retrieval introduces topical distractors. This challenge is not tied to a particu?lar knowledge-base format. Candidate pools may come from standalone retrievers, standard RAG backends, or graph-based retrieval pipelines. What is needed is a query-aware selection layer that can use relational structure to filter candidates be?fore generation. PAGE-RAG addresses this setting by using a graph as a temporary selection structure, rather than assum?ing a graph-structured knowledge base. It builds a query-local graph over retrieved candidates, records why candidates are connected, and treats each connection as a support hypothe?sis rather than support itself. We identify the resulting failure mode as a connectivity-support gap: connected candidates do not necessarily support the answer. We propose PAGE-RAG, a Provenance-Aware Graph Evidence promotion method that scores candidate paths with relevance, source-tracing meta?data, specificity, hubness, noise, and coherence signals, and applies minimal sufficient selection to promote supporting facts into a compact reader context. PAGE-RAG can serve as a complete retrieval-to-reading pipeline, and the same promo?tion stage can be inserted after existing retrieval or RAG sys?tems without replacing their upstream retrieval logic. Across three multi-hop QA benchmarks under the same final bud?get, PAGE-RAG improves support F1 and answer F1 by 10.4 and 3.3 points on a weighted average over a strong retriever. As a plug-in, PAGE-RAG further improves all reported RAG backends, including reasoning-oriented, compression-based, graph-based, and document/chunk-level systems.

Autonomous AI agents now transact at production scale -- 69,000 bots executing 165 million transactions across 50 million USDC in cumulative volume on a single marketplace -- without any shared trust layer between participants. Regulatory frameworks (Singapore IMDA, NIST CAISI, EU AI Act) and major AI laboratories (Anthropic, Google) have independently converged on the same structural requirement: an open, portable, cryptographically verifiable trust infrastructure for autonomous agents that no single vendor can deliver alone. This paper presents MolTrust, a production-deployed implementation of such an infrastructure built on W3C Verifiable Credentials 2.0 and Decentralized Identifiers v1.0, with on-chain anchoring on Base Layer 2. The system architecture is organized around four primitives (identity, authorization, behavioral record, portability), a five-party accountability chain, and the Agent Authorization Envelope (AAE) -- a machine-evaluable authorization structure enforced at three layers: cryptographic signatures, API-level credential lifecycle management, and kernel-level syscall monitoring via Falco eBPF integration. The paper documents three distinguishing capabilities: kernel-layer AAE enforcement below the agent process boundary; cross-protocol interoperability through five reproducible test vectors verified against independent implementations; and layered Sybil resistance combining dual-signature interaction proofs, cross-vertical endorsement diversity gating, and principal-DID-linked violation persistence. The reference implementation has been operational since March 2026 across eight credential verticals. Empirical validation at adversarial scale is pending. The contribution is deployment-first evidence that the trust infrastructure regulators and industry have converged on is implementable today using W3C-standardized primitives.

Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context. We introduce PRISM (Population-Retrieved Inference for Structured Multimodal Prognosis), a multimodal language model that combines per-feature numerical tokenization, recency-weighted aggregation of longitudinal ECGs, and a dual-modality population memory bank. Retrieval operates in representation space: the model receives mean-pooled embeddings of similar training-cohort encounters, while no individual retrieved record enters the prompt. On the 1,443-task MDS-ED benchmark, PRISM achieves AUROCs of 86.2% for diagnosis, 93.1% for deterioration, 91.8% for ICU admission, and 92.8% for mortality. These results use a 96-hour pre-arrival window unavailable to reported baselines. With benchmark-window inputs only, PRISM reaches 0.8895 AUROC, compared with 0.8937 for UniPACT and 0.8889 for MDS-ED. A matched-input compact fusion model using the same five evidence streams and frozen encoders reaches 0.7652 AUROC, versus 0.9092 for PRISM. Replacing numerical EHR encoding with text serialization reduces AUROC by 3.66 points; removing pre-arrival history reduces it by 1.97 points; and zeroing retrieval reduces it by 0.99 points. Genuine retrieval outperforms random-neighbor retrieval by 0.97 macro-average points, although a paired task-level sign test does not establish a uniform advantage (p=0.067). On the external MC-MED cohort, supervised fine-tuning reaches 0.8611 AUROC, compared with 0.8227 for locally trained gradient boosting and 0.7841 for source-only PRISM. These results support structure-aware multimodal integration and supervised external adaptation.

Firm characteristics are commonly represented as fixed vectors, even though evidence about firms' operations arrives as heterogeneous collections of articles reports. We study how distances between distributions of firm characteristics restrict systematic covariance. For given latent exposure laws, quadratic Wasserstein geometry yields sharp covariance endpoints over admissible couplings. Under a common randomized bi-Lipschitz characteristic-to-exposure map, bounded risk-coordinate slack, and a maintained return-covariance bridge, characteristic-side distance yields a conditional interval for the covariance ceiling. Greater separation then leaves less scope for aligned systematic exposures when these assumptions are tight, while a non-negative transport excess term records the gap between realized and maximum-covariance arrangements. The resulting envelope is scenario analysis rather than an expected-return, no-arbitrage, or identified structural model. Empirically, we proxy characteristic distributions with encoder-only language-model embeddings of financial news articles, disclosures, and analyst reports for Nasdaq firms over 2018-2022. In a dyadic regression with symmetric firm effects, greater pairwise article-embedding W2 distance is associated with weaker return co-movement: the coefficient is 1.920, with 95% interval [1.412, 2.468]. The estimate retains the same sign when returns are measured in a later window, although the feature construction is not point-in-time and the evidence remains reduced form.

Stellar flare events are critical observational samples for astronomical research; however, recorded flare events remain limited. Stellar flare forecasting can provide additional flare event samples to support research efforts. Despite this potential, no specialized models for stellar flare forecasting have been proposed to date. In this paper, we present extensive experimental evidence demonstrating that both stellar physical properties and historical flare records are valuable inputs for flare forecasting tasks. We then introduce FLARE (Forecasting Light-curve-based Astronomical Records via features Ensemble), the first-of-its-kind large model specifically designed for stellar flare forecasting. FLARE integrates stellar physical properties and historical flare records through a novel Soft Prompt Module and Residual Record Fusion Module. Our experiments on the publicly available Kepler light curve dataset demonstrate that FLARE achieves superior performance compared to other methods across all evaluation metrics. Finally, we validate the forecast capability of our model through a comprehensive case study.

Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-modal conflict remains underexplored. Existing benchmarks conflate two distinct forms of evidence within a single modality: perceptual signals (e.g., a photograph or recording of a dog) and propositional signals (e.g., the declarative claim "this is a dog"), such that any measured modality bias is inherently confounded with evidence-form bias, precluding clean attribution to either source. To address this, we introduce Tri-PvP, an 8,000-sample tri-modal conflict benchmark crossing vision, audio, and text, where vision and audio each take perceptual or propositional form. Evaluating five OLLMs, we find robust visual bias across most models and evidence-type conditions. Crucially, we reveal a systematic asymmetry in evidence-form bias: models exhibit a stronger bias toward perceptual signal in vision but propositional in audio. Further analyses via layer-wise linear probing and contrastive decoding reveal that modality bias is already linearly decodable from early representation layers and can only be partially mitigated, calling for mitigation strategies beyond surface-level interventions.

Large language models (LLMs) generate fluent text across a wide range of tasks, but the fabrication of non-existent academic citations remains a critical and well-documented failure mode. Building on prior work that frames hallucination and verbatim memorization as outcomes of the same probabilistic process, this study uses citation count as a proxy for training data redundancy and asks how this redundancy is internally structured within a single bibliographic record. Using GPT-4.1, we generated and manually verified 100 citations across twenty computer-science domains, measuring factual fidelity via cosine similarity against authentic metadata. We find that (i) factual accuracy varies substantially across domains and scales log-linearly with citation count, (ii) the model crosses two empirically identifiable thresholds; an inflection around 90 citations and a saturation point near 1,200 citations beyond which records are reproduced nearly verbatim, (iii) memorization is hierarchical, with titles and first authors recalled earliest while venues and numeric fields require far greater redundancy and publication years remain essentially unlearned, and (iv) even highly cited records can be conflated when their titles and authors overlap, an effect interpretable as spurious-attractor interference. Memorization in LLMs is therefore not a binary on/off state but a graduated, hierarchically layered phenomenon shaped by the uneven distribution of knowledge in the pretraining corpus.

Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as isolated local instances. This is limiting because beat labels often depend on multi-beat rhythm context, including timing, compensatory pauses, and beat-to-beat morphological consistency. We present DeepArrhythmia, a tool-grounded multimodal framework for segment-contextualized beat-level ECG arrhythmia classification. Given a multi-beat ECG segment, DeepArrhythmia combines the raw ECG signal and a rendered waveform image, localizes R peaks to identify beat instances, and produces structured beat-level predictions. The framework decouples physiological measurement from evidence integration using specialized tools for beat localization, numerical rhythm--morphology extraction, and morphology-focused textual analysis. DeepArrhythmia uses segment-level confidence to route between minimal and rich evidence states, since richer physiological evidence is not uniformly useful. This agentic design integrates rhythm context, explicit physiological grounding, and selective evidence acquisition for decision making.

The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled. Compared with harness optimization for non-GUI agents, automatically optimizing this harness poses three coupled challenges: reconciling model intent with observed visual effects, diagnosing failures under variable execution outcomes, and identifying recurrent failure patterns across tasks and translating them into reusable runtime changes. We introduce GUI-HARVEST, an automatic harness optimizer that enables self-improving GUI agents with frozen backbone models. First, to ground diagnosis in observed action effects, it aligns model outputs and executed actions with before-and-after screenshots, tying findings to specific interface transitions. Second, to account for execution variability, it treats repeated runs of the same task as a joint evidence unit, using within-task comparisons to locate outcome-relevant behavioral differences. Third, it consolidates verified findings across tasks into recurring failure patterns, maps them to bounded source-code edits with predictions recorded before evaluation, and checks the predicted behavioral effects alongside task performance through repeated execution. Experiments on OSWorld-Verified show consistent held-out gains across six general-purpose open, GUI-specialized open, and proprietary backbone models; Qwen3-VL-32B-Instruct gains 12.33 points on the full suite. Frozen-harness transfer improves GPT-5 by 13.87 percentage points on WindowsAgentArena at 50 steps without further optimization. With the same backbone and initial harness, GUI-HARVEST outperforms Self-Harness and Meta-Harness, suggesting that GUI-specific diagnosis and validation help harness improvements generalize to unseen tasks. The code is available at https://github.com/GaryYang12345/GUI-HARVEST.

Clinical evidence, derived from rigorous research and data analysis, provides healthcare professionals with reliable scientific foundations for informed decision-making. Integrating clinical evidence into real-time practice is challenging due to the enormous workload, complex professional processes, and time constraints. This highlights the need for tools that automate evidence synthesis to support more efficient and accurate decision making in clinical settings. This study introduces Quicker, an evidence-based clinical decision support system powered by large language models (LLMs), designed to automate evidence synthesis and generate clinical recommendations modeled after standard clinical guideline development processes. Quicker implements a fully automated chain that covers all phases, from questions to clinical recommendations, and further enables customized decision-making through integrated tools and interactive user interfaces. To evaluate Quicker's capabilities, we developed the Q2CRBench-3 benchmark dataset, based on clinical guideline development records for three different diseases. Experimental results highlighted Quicker's strong performance, with fine-grained question decomposition tailored to user preferences, retrieval sensitivities comparable to human experts, and literature screening performance approaching comprehensive inclusion of relevant studies. In addition, Quicker-assisted evidence assessment effectively supported human reviewers, while Quicker's recommendations were more comprehensive and logically coherent than those of clinicians. In system-level testing, collaboration between a single reviewer and Quicker reduced the time required for recommendation development to 20-40 minutes. In general, our findings affirm the potential of Quicker to help physicians make quicker and more reliable evidence-based clinical decisions.

Historical Arabic manuscript transcription is not only a recognition problem. A usable scholarly system must cope with shifting hands and layouts, preserve uncertain readings, distinguish visual evidence from linguistic plausibility, and record the researcher's final decision. We present Phoenix, a 4.99-million-parameter CNN-BiLSTM-CTC recognizer, and Athar, an evidence-aware review workflow built around it. Phoenix is adapted across archival, Maghrebi, and historical manuscript domains using document-aware replay, an expanded 81-symbol codec, and forgetting guards that reject checkpoints that improve a new domain at unacceptable cost to previous domains. In a pre-specified held-out comparison against the preceding checkpoint, frozen before evaluation and scored with greedy decoding and raw references, Phoenix reduced CER from 22.12% to 17.86% on 10,594 Agapet lines and from 17.72% to 11.84% on 11,684 Omar lines, while regressing from 10.39% to 10.72% on 164 TariMa lines. Across the two large held-out sets, character-weighted CER fell from 19.98% to 14.93%, a 25.3% relative error reduction. A separate same-protocol development diagnostic found the lowest CER for Phoenix on four of four comparable domains (9.59% unweighted macro CER). An N-best diagnostic revealed a 2.15-point oracle gap between beam decoding and Oracle@25, while neural text rerankers, consensus MBR, CTC-posterior quality estimation, and local pre-CTC hidden-state quality estimation recovered less than 4% of this gap. Athar therefore preserves the visual reading, exposes bounded alternatives, uses local language models conservatively, retrieves source parallels with unique, ambiguous, or abstain states, and exports auditable TEI and PAGE-XML records. The results support evaluating manuscript HTR as auditable evidence management rather than silent text replacement.

Clinical decision-making increasingly relies on timely and context-aware access to patient information within Electronic Health Records (EHRs), yet most existing natural language question-answering (QA) systems are evaluated solely on benchmark datasets, limiting their practical relevance. To overcome this limitation, we introduce EHRNavigator, a multi-agent framework that harnesses AI agents to perform patient-level question answering across heterogeneous and multimodal EHR data. We assessed its performance using both public benchmark and institutional datasets under realistic hospital conditions characterized by diverse schemas, temporal reasoning demands, and multimodal evidence integration. Through quantitative evaluation and clinician-validated chart review, EHRNavigator demonstrated strong generalization, achieving 86% accuracy on real-world cases while maintaining clinically acceptable response times. Overall, these findings confirm that EHRNavigator effectively bridges the gap between benchmark evaluation and clinical deployment, offering a robust, adaptive, and efficient solution for real-world EHR question answering.

Much of expressive text-to-speech research rests on an untested assumption that written text carries enough information to select an appropriate prosodic style for its delivery. Text-predicted style models improve listener preference, and expressive-appropriateness evaluation presupposes that context constrains style, yet neither measures the assumption itself. This paper tests it as a falsifiable hypothesis against style labels derived from acoustics alone. For each of six speakers in a 1,200-hour conversational corpus, utterances are clustered in the spaces of five speech models, including a prosody-only control, and the cluster of held-out utterances is predicted from twelve text embedding models. Three controls are applied: utterance length is erased from the speech embeddings; accuracy is scored against the majority-class floor of unbalanced clusters rather than uniform chance; and a bag-of-words baseline measures word identity alone. Text predicts the cluster above that floor for all six speakers (+0.111 top-3 accuracy), but bag-of-words achieves three quarters of this. Sentence embeddings add only +0.026, largest for encoders not trained for sentence semantics and reversed by tree-based probes for all others. Acoustic clusters are not compact in text embedding space in any of 360 configurations. The prosody-only space weakens the association for five speakers, but not for the speaker showing it most strongly. Text thus informs these delivery clusters mainly through word choice, whether as a cue to prosody or as a marker of topic and recording situation, and reference-free style selection cannot assume more.

Brain MRI interpretation is a longitudinal clinical reasoning problem: radiologists compare serial studies, integrate information across MRI sequences, localize findings within volumetric anatomy, and translate this evidence into report-grounded assessments. Existing medical VQA and 3D imaging benchmarks capture important parts of this workflow, but often evaluate brain MRI through isolated images, static volumes, or ungrounded report-style answers, thereby obscuring failures in the evidence chain that support clinical validity. We introduce BrainTRACE, a report-grounded benchmark for evaluating whether vision-language models can trace the evidence structure required for longitudinal brain MRI interpretation. BrainTRACE contains 7,273 scored VQA instances derived from 1,778 longitudinal patients, 7,299 MRI studies, and approximately 29k co-registered 3D MRI sequence volumes. The benchmark is organized by five levels of clinical reasoning, from acquisition recognition to case-level synthesis, and by evidence demands covering longitudinal comparison, report-grounded references, multi-sequence integration, and volumetric spatial evidence. BrainTRACE supports rendered inputs compatible with standard VLM interfaces, a 3D-evidence condition, and a decomposed case-reasoning track that audits six steps in a longitudinal evidence chain. Evaluation of 20 VLM configurations shows that current systems can identify isolated visual cues but rarely compose them into grounded longitudinal interpretations. We release the benchmark specification, evaluation lists, scoring implementation, scoring rubrics, and audit-record format to support reproducible progress in brain MRI VLM evaluation.

Most video-retrieval systems assume a bounded corpus and return ranked files or timestamps. Agents operating over cameras, screens, streams, and archives face a different systems problem: observations arrive continuously; models interpret them at different temporal granularities; context must be selected without replaying the complete visual record; and results must stay connected to inspectable source evidence. We argue that search over such a corpus is an infrastructure problem that cannot be reduced to ranking video files. We develop a conceptual and formal model of search over the visual world built on analyzer-defined scenes, persistent understanding artifacts, visual memory as coexisting scene spaces over shared source time, and capability-declared indexes, distinguishing memory (everything retained), context (what is selected for a task), and evidence (the source intervals that ground it). The VideoDB data format (VDB) realizes this model in production, exposed through a typed search surface spanning planned retrieval, stateful investigation, direct access, and grounded synthesis. We contrast this model-agnostic infrastructure, where segmentation, sampling, model choice, embeddings, and ranking are system decisions and live streams are first-class sources, with video-native foundation models offered as fixed APIs. In a semantic-retrieval comparison against a commercial video-native engine spanning 9,800+ queries over four public datasets, a pipeline of general-purpose components achieves higher macro-averaged Recall@1/@3/@10 (73.09/83.39/91.20 versus 65.75/77.13/89.10), while the baseline is higher at Recall@50 (96.42 versus 96.07). Retrieval quality over the visual world is today governed more by system design than by video-specific pretraining, and visual-memory infrastructure can deliver it while keeping playable, source-grounded evidence first-class.

We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record.

Autonomous scientific agents now increasingly propose ideas, write code, run experiments, analyze results, and even draft papers. Observe and audit those agents are necessary but logging every model call is not enough, scientists also need to inspect the artifacts and claims that the systems produced and their relations. This is driven by the fact that failures in scientific agent systems are often distributed across several objects. A manuscript claim may cite the wrong evidence, a search process may select a degenerate candidate, a laboratory novelty claim may depend on an unstated rule, or a multi-agent plan may change without a visible trigger. Existing tracing, experiment tracking, and archival provenance tools are valuable, but their native objects do not make these scientific audit relations first-class. We argue that autonomous scientific systems should emit portable, claim-aware artifact lineage as a minimum audit layer. We propose a compact observability profile organized around individuals, operators, fitness records, lineage, archives, runs, streams, and steering commands. In this profile, scientific claims are ordinary individuals with explicit evidence bindings and verification records. The profile is intended as a semantic layer that complements current telemetry and provenance standards. Execution details can remain in OpenTelemetry. Final packages can export to PROV-O or RO-Crate standards.

LLM agents increasingly rely on external inference conditions: prompts, tools, memory, SOPs, skills, and harness feedback. These assets can improve task execution without changing model weights, but they are often revised by heuristic reflection or by reusing observed successes and failures as if counts alone were reliable belief. We introduce Bayesian-Agent, a native and cross-harness framework that treats reusable skills and SOPs as hypotheses about whether a frozen model will succeed under a particular prompt, context, and harness environment. Bayesian-Agent records verified trajectory evidence, maintains a feature-conditioned categorical posterior over each skill, and maps posterior state into inspectable actions such as patch, split, compress, retire, and explore. Model-facing prompts receive executable guardrails and failure-mode patches, while posterior summaries remain available for audit. With deepseek-v4-flash, incremental repair improves SOP-Bench from 80\% to 95\%, Lifelong AgentBench from 90\% to 100\%, and RealFin-Bench from 45\% to 65\%. We further evaluate Bayesian-Agent's native backend and optional GenericAgent, mini-swe-agent, and Claude Code backends. The results include positive, negative, saturated, and case-study settings, suggesting that agent skill evolution is best viewed as posterior-guided harness optimization rather than uncalibrated prompt accumulation. The source code is available at https://github.com/DataArcTech/Bayesian-Agent.

Italy exhibits rich linguistic diversity across its territory due to the distinct regional languages spoken in different areas. Recent advances in self-supervised learning provide new opportunities to analyze Italy's linguistic varieties using speech data alone. This includes the potential to leverage representations learned from large amounts of data to better examine nuances between closely related linguistic varieties. In this study, we focus on automatically identifying the geographic region of origin of speech samples drawn from Italy's diverse language varieties. We leverage self-supervised learning models to tackle this task and analyze differences and similarities between Italy's regional languages. In doing so, we also seek to uncover new insights into the relationships among these diverse yet closely related varieties, which may help linguists understand their interconnected evolution and regional development over time and space. To improve the discriminative ability of learned representations, we evaluate several supervised contrastive learning objectives, both as pre-training steps and additional fine-tuning objectives. Experimental evidence shows that pre-trained self-supervised models can effectively identify regions from speech recording. Additionally, incorporating contrastive objectives during fine-tuning improves classification accuracy and yields embeddings that distinctly separate regional varieties, demonstrating the value of combining self-supervised pre-training and contrastive learning for this task.

Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer from three critical limitations: (1) trajectory-opaque grading that checks only final outputs, (2) underspecified safety and robustness evaluation, and (3) narrow modality coverage and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps. It comprises 300 human-verified tasks spanning 9 categories across three groups (general service orchestration, multimodal perception and generation, and multi-turn professional dialogue). Every agent action is recorded through three independent evidence channels (execution traces, audit logs, and environment snapshots), enabling trajectory-aware grading over 2,159 fine-grained rubric items. The scoring protocol evaluates Completion, Safety, and Robustness, reporting Average Score, Pass@k, and Pass^k across three trials to distinguish genuine capability from lucky outcomes. Experiments on 14 frontier models reveal that: (1) trajectory-opaque evaluation is systematically unreliable, missing 44% of safety violations and 13% of robustness failures that our hybrid pipeline catches; (2) controlled error injection primarily degrades consistency rather than peak capability, with Pass^3 dropping up to 24% while Pass@3 remains stable; (3) multimodal performance varies sharply, with most models performing poorer on video than on document or image, and no single model dominating across all modalities. Beyond benchmarking, Claw-Eval highlights actionable directions for agent development, shedding light on what it takes to build agents that are not only capable but reliably deployable.

Agent Skills have become persistent behavioral artifacts across independent AI agent systems. They combine natural-language task specifications with metadata and optional references, scripts, assets, hooks, package manifests, tests, and companion interfaces. Existing studies explain how Skills are specified, executed, maintained, and evolved, but lack an ontology that defines these artifacts as independent software objects. This paper introduces Skillware as the software abstraction that extends software engineering to persistent Behavioral Artifacts in agent systems. A Skill Artifact specifies reusable task behavior; a Skillware Unit manages that artifact as software through an independent identity and lifecycle. A compatible Agent Host activates the unit for runtime interpretation. Three necessary conditions operationalize category membership: behavioral primacy, independent software identity, and an Agent Host execution relationship. Lifecycle Continuity records whether the same unit identity persists through update, maintenance, rollback, and removal as a separate software-grade property. Evidence combines the Agent Skills specification, a frozen corpus of 138,133 content-deduplicated SKILL.md records associated with 20,556 repository identifiers, independent empirical studies, 15 category-boundary cases, and 13 fixed-revision engineering implementations. The evidence establishes a recurring artifact envelope, separable software identities, compatible execution paths, and lifecycle engineering pressure. Skillware provides the software ontology and engineering lifecycle through which agent capabilities can become identifiable, composable, maintainable, and evolvable software artifacts.

Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after each interaction to extract, summarize, or update memories. This design makes memory construction increasingly costly as conversations grow. Coarse summarization can reduce construction cost but risks discarding fine-grained contextual evidence, whereas larger retrieval contexts or multi-hop LLM reasoning shift the overhead to query time. We present LycheeMemory V2, an efficient long-term memory framework that replaces turn-level consolidation with semantic segment-level consolidation. Instead of consolidating every interaction, LycheeMemory batches multiple exchanges into segments and encodes each finalized segment into context-independent typed memory records. Segment-level batching lowers LLM encoding frequency, while semantic boundary detection helps preserve coherent event-level and temporal evidence compared with fixed-window batching. The resulting records are organized with lightweight structured indexes for query-planned evidence retrieval. Experiments using GPT-4.1-Mini show that LycheeMemory achieves state-of-the-art performance, reaching 89.22% on LoCoMo and 92.20% on LongMemEval-S. Compared with A-Mem, it reduces construction tokens by 86.0% on LoCoMo and 75.9% on LongMemEval-S without increasing query-time token usage. More broadly, our results suggest that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the granularity at which it is consolidated.

An AI scientist should not grade its own homework. Yet in the systems we examined, the agent that reviews the work usually comes from the same model family as the agent that produced it, or at least from the same vendor. Model evaluators are known to favour their own generations. Whether models trained alike also share blind spots is a conjecture, not a settled finding, but if they do, the reviewer inherits the author's. The record of what was flagged and what was waved through often sits in platform logs that nobody outside can replay. We present CrossAudit, a protocol for supervising autonomous research pipelines. It rests on three commitments. Each increment of work is audited by an agent from a different vendor against a rulebook a human wrote and versioned. Reports, verdicts, disputes and rulings are git commits, so the supervision history can be re-read and cited; raw model exchanges are not yet part of that record. Scripted checks run before any model does. Advisory judgement never gates the pipeline: a model blocks only by citing a rule, and no model may waive a deterministic failure. Blockers that survive a bounded number of revision rounds go to a person. We state the protocol as eight invariants. We describe a reference implementation built from GitHub Actions and a few hundred lines of Python, and report a live deployment of a closely related variant in a computational-chemistry pipeline. We also ran a seeded-defect trial (30 increments, 43 seeded defects, one run per configuration). A cross-vendor audit of our own repository then voided its blinding. We adopt that audit's findings and report the corrected results. The trial shows that two vendors read the same rulebook differently. It does not show that either is better. The strongest evidence here is the committed, uncontrolled record of cross-vendor audits of this paper itself.

Real-world Earth observation (EO) agents must translate high-level scientific questions into executable workflows to acquire observations, prepare data, perform domain computations, and derive conclusions from runtime evidence. Existing EO agents typically start from supplied observations, while benchmarks typically provide prepared inputs or candidate answers, leaving full-chain open-world EO execution largely untested. We present Earth-Agent-Pro, an execution-adaptive Plan-and-Execute framework using expert-authored skills to constrain planning and runtime tool use. Workflow-centered structured memory records planned steps, accepted evidence, and their dependencies, enabling repair of only the affected workflow suffix when runtime evidence invalidates a step. Separate large language model adapters use sequence-level supervised fine-tuning for planner workflow composition and node-level group relative policy optimization with locally verifiable rewards for executor tool-argument grounding. Earth-Bench-Pro instantiates 248 expert-curated task cores as 744 questions under three matched regimes. Its 248 Open-World Execution questions span RGB imagery, spectral observations, and remote sensing products, pairing high-level requests with runtime data requirements, executable trajectories, and open-ended answers grounded in execution evidence. With a shared GPT-5 backbone, Earth-Agent-Pro achieves 66.13% LLM-as-Judge accuracy, exceeding ReAct by 20.95 points in this metric and 24.44 points in Tools-In-Order. Joint adapter tuning raises Qwen3.5-9B LLM-as-Judge accuracy from 38.31% to 50.00%, an 11.69-point gain over the untuned configuration. Planning-only evaluation and execution with the reference workflow show that the adapters improve workflow composition and argument grounding, respectively. Code and datasets will be released soon.

Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This raises a natural question: can long-horizon context instead be organized around reusable progress rather than the history that produced it? In this paper, we introduce CarryOn, an object-oriented context runtime that organizes continuation around reusable task objects. Rather than treating compressed histories or reconstructed accounts of progress as the primary basis for continuation, CarryOn builds a context view from continuation carriers, complementary execution context, and a live tail of recent interactions. A core challenge is keeping this reusable basis valid after its surrounding history is retired: how can CarryOn update the basis without reconstructing the full representation at every fold? CarryOn maintains carrier records across folds, revising affected records against bound evidence and applicable environment checks while carrying forward unaffected records and jointly updating execution context. Experiments on OSWorld 2.0 and BrowseComp-Plus show improved gains of 5.8% and 7.0% while reducing total token usage by 51.9% and 22.9%, respectively. Project page: https://ethannju.github.io/carryon

Understanding the brain increasingly depends on integrating evidence across scales, modalities, and disciplines. Addressing a single research question therefore requires a coordinated sequence of operations, from surveying prior work to executing analyses and interpreting results in light of domain knowledge. AI agents promise to accelerate this process, but current agents lack domain expertise in brain science, may fabricate claims, drift during multi-step reasoning, and offer few defined points for expert intervention. These failures are especially costly in brain science, where conclusions feed into downstream scientific claims and depend on laboratory-specific expertise and careful human judgment. We present BrainPilot a fully open-source multi-agent system that accelerates brain science research with traceable logs and agent-verified results. A principal investigator (PI) agent coordinates specialist agents grounded in curated domain knowledge: a unified brain science knowledge base containing 7{,}233 indexed items and a skill library of 72 reusable methodology units across seven research domains. Every major step is recorded in the Graph of Trace, an auditable record that links subgoals, tool use, evidence, and claims and allows researchers to follow and inspect the workflow. An Auditor agent further integrates fabrication checking into the workflow. For evaluation, we run three brain science tasks from Agents' Last Exam, introduce our own benchmark, BrainPilotBench-v0, and present additional end-to-end case studies. Across these evaluations, BrainPilot with an open-source backbone model attains performance comparable to state-of-the-art agent framework with less costs.

Earthquakes are evaluated among the most destructive disasters for human beings, as also experienced for Turkiye region. Data science has the property of discovering hidden patterns in case a sufficient volume of data is supplied. Time dependency of events, specifically being defined by co-occurrence in a specific time window, may be handled as an associate rule mining task such as a market-basket analysis application. In this regard, we assumed each day's seismic activity as a single basket of events, leading to discovering the association patterns between these events. Consequently, this study presents the most prominent association rules for the earthquakes recorded in Turkiye region in the last 5 years, each year presented separately. Results indicate statistical inference with events recorded from regions of various distances, which could be further verified with geologic evidence from the field. As a result, we believe that the current study may form a statistical basis for the future works with the aid of machine learning algorithm performed for associate rule mining.

Rare diseases affect hundreds of millions worldwide, yet diagnosis often spans years. Convectional pipelines decouple noisy evidence extraction from downstream inferential diagnosis, and general/medical large language models (LLMs) face scarce real world electronic health records (EHRs), stale domain knowledge, and hallucinations. We assemble a large, domain specialized clinical corpus and a clinician validated reasoning set, and develop RareSeek R1 via staged instruction tuning, chain of thought learning, and graph grounded retrieval. Across multicenter EHR narratives and public benchmarks, RareSeek R1 attains state of the art accuracy, robust generalization, and stability under noisy or overlapping phenotypes. Augmented retrieval yields the largest gains when narratives pair with prioritized variants by resolving ambiguity and aligning candidates to mechanisms. Human studies show performance on par with experienced physicians and consistent gains in assistive use. Notably, transparent reasoning highlights decisive non phenotypic evidence (median 23.1%, such as imaging, interventions, functional tests) underpinning many correct diagnoses. This work advances a narrative first, knowledge integrated reasoning paradigm that shortens the diagnostic odyssey and enables auditable, clinically translatable decision support.

AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference. Here we introduce Xcientist, a research harness that externalizes research synthesis and experimental validation into inspectable, contract-governed processes. Xcientist organizes literature evidence, idea states, implementation plans, ablation records and repair traces as persistent research artifacts, so that generated mechanisms can be grounded, executed, tested and revised without losing their evidential basis. We identify claim drift as a failure mode of automated research, where runnable artifacts no longer support the mechanism originally claimed. Across training-free memory systems, graph-structured traffic forecasting and multi-scale physics-informed neural networks, Xcientist preserves traceable trajectories from problem formulation to mechanism design, validation and bounded revision. These results suggest that AI scientists should be evaluated not only by their final artifacts, but by whether their synthesis and validation processes remain attributable, inspectable and scientifically accountable.

Agent skills extend language-model agents with task-specific procedures, scripts, and references, but the tasks and environments they target continually change. Existing methods improve skills in bounded runs and retain only the final artifact, discarding the decision history that later agents need to interpret prior revisions, evaluations, and rejected alternatives. We introduce SkillHone, a harness for continual agent skill evolution grounded in persistent decision history. SkillHone pairs skill revisions with evaluation-side evidence that supplies practice feedback, recording structured histories of diagnoses, revisions, evidence, and outcomes. Role-separated subagents run candidate skills on practice probes with redacted reporting and propose revisions informed by prior decisions, enabling cross-session refinement without rediscovering past rationale. On deep-research benchmarks, SkillHone runs without a pre-integrated search stack and outperforms the commercially backed deep-research agent by 15.8 points on GAIA and 3.2 points on WebWalkerQA-EN, while also exceeding prior skill-evolution methods. We further deploy SkillHone on internal tool-mediated analysis scenarios, where it improves accuracy by an average of 18.8 points across seven settings.

Modern multi-agent knowledge systems increasingly accumulate knowledge through chains of autonomous transformations rather than direct retrieval. Existing provenance work records what happened - execution traces, tool calls, evidence links - and source-reliability estimation is long established (truth discovery, reputation systems). What is missing is an operational framework that attaches graded, per-domain transmitter reliability to claim-level transmission chains, with completeness semantics, transformation-typed aggregation, decoupled content criticism, and serve/review/quarantine routing. Classical Islamic hadith science confronted a structurally similar problem: deciding whether knowledge transmitted through chains of human narrators should be accepted. Over centuries it developed a rigorous methodology - isnad (a complete transmission chain attached to every claim), rijal (systematic grading of each narrator's integrity and precision), weakest-link chain evaluation, corroboration through independent chains, and matn criticism (content evaluated independently of chain quality). This paper transfers that methodology to AI system design. We contribute a formal mapping from hadith-science concepts to multi-agent pipelines, a relational schema implementing claim chains and a graded narrator registry, a decision matrix combining chain grade with content criticism, and an evaluation on 20,000 claims from real physics textbooks. The evaluation validates weakest-link quarantine and independent-chain corroboration; reports a partial failure of the grade-recovery loop, which missed the highest-fault narrator; and reports two analyses as inconclusive, including a matched-coverage comparison the framework could not reach with the reference content critic. The paper is explicit throughout about which claims the evidence does and does not yet support.

Long-form audio analysis requires systems to localize and integrate evidence distributed across extended recordings. While existing work primarily retrieves semantic content through structured textual representations, many real-world queries depend on acoustic evidence that is better preserved in continuous representations or raw audio. We introduce HARP (Hybrid Audio Retrieval Pipeline), an agentic framework and benchmark for systematically studying retrieval and evidence representations in long-audio analysis. Hybrid retrieval combining keyword and vector search shows the most robust performance. When paired with both metadata and retrieved audio as evidence, average answer accuracy improves by around 10% and rationale accuracy by around 6% over single-modality retrieval and evidence. Fine-grained evaluation shows that answer accuracy alone overestimates system capability and that HARP mostly follows human performance trends across query types. These results highlight the importance of combining structured retrieval with flexible access to audio evidence and evaluating long-audio systems beyond answer accuracy.

Routine inspection of power distribution infrastructure remains challenging for utilities operating geographically dispersed networks, where conventional manual inspection can be difficult to perform consistently and at scale. This work presents a smartphone-based AI inspection system for assessing targeted distribution-infrastructure conditions from images captured by field personnel. The proposed workflow integrates image-quality and viewing-perspective validation with AI-assisted assessment of pole lean, crossarm and top-cleat tilt, voltage level, vegetation-clearance risk, and distribution-transformer (DTR)-ground clearance. The system integrates deep-learning models with monocular depth estimation, geometric analysis, and rule-based processing within a common multi-stage inspection workflow designed for practical field operation. The system was pilot deployed across five selected distribution feeders within the Eastern Power Distribution Company of Andhra Pradesh Ltd. (APEPDCL), where 1,222 defect instances were identified across the assessed categories and subsequently tracked through a rectification and verification workflow, with 84 defect instances recorded as rectified during the study period. Feeder-level interruption records were also examined over the study period; however, the available observations do not provide sufficient evidence to establish a reliability improvement attributable to the proposed system. A curated multi-module field-captured dataset, PD-Defect, is also publicly released to support reproducible research in distribution-infrastructure inspection. The field deployment demonstrates the practical integration of smartphone-based AI-assisted inspection into field inspection and maintenance activities, providing a mechanism for systematic identification, documentation, rectification tracking, and verification of targeted distribution-infrastructure defects.

Biomedical knowledge graphs (KGs) encode vast, heterogeneous information spanning literature, genes, pathways, drugs, diseases, and clinical trials, but leveraging them collectively for scientific discovery remains difficult. Their structural differences, continual evolution, and limited cross-resource alignment require substantial manual integration, limiting the depth and scale of knowledge exploration. We introduce DeepEvidence, an AI-agent framework designed to perform Deep Research across various heterogeneous biomedical KGs. Unlike generic Deep Research systems that rely primarily on internet-scale text, DeepEvidence incorporates specialized knowledge-graph tooling and coordinated exploration strategies to systematically bridge heterogeneous resources. At its core is an orchestrator that directs two complementary agents: Breadth-First ReSearch (BFRS) for broad, multi-graph entity search, and Depth-First ReSearch (DFRS) for multi-hop, evidence-focused reasoning. An internal, incrementally built evidence graph provides a structured record of retrieved entities, relations, and supporting evidence. To operate at scale, DeepEvidence includes unified interfaces for querying diverse biomedical APIs and an execution sandbox that enables programmatic data retrieval, extraction, and analysis. Across established deep-reasoning benchmarks and four key stages of the biomedical discovery lifecycle: drug discovery, pre-clinical experimentation, clinical trial development, and evidence-based medicine, DeepEvidence demonstrates substantial gains in systematic exploration and evidence synthesis. These results highlight the potential of knowledge-graph-driven Deep Research to accelerate biomedical discovery.

Scientific ideation unfolds over multiple stages, including literature search, paper reading, tool use, claim checking, cross-paper synthesis, brainstorming, rejection of weak directions, and iterative writing. Yet most existing resources capture isolated components or final artifacts rather than the process connecting them. We introduce IdeaTrail, a dataset of 1,170 multi-turn trajectories for scientific ideation and proposal generation. Each trajectory follows a research process from evidence gathering to either idea selection or proposal construction, jointly recording tool use, acquired evidence, intermediate artifacts, and reasoning. IdeaTrail is synthesized from human-selected research papers and proposal artifacts through a Generator--Advisor loop. The Generator produces the visible sequence of actions, observations, and artifact edits, while the Advisor uses the full generation context to check grounding, causal order, naturalness, and leakage from hidden targets. This reverse-to-forward design keeps trajectories aligned with real scientific artifacts while retaining the uncertainty, evidence use, and staged convergence characteristic of research practice. IdeaTrail provides both reusable process supervision and a general recipe for constructing scientific-research-agent data.

Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often store observations as isolated records, summaries, or indexed fragments, which makes evidence aggregation, fact revision, and memory maintenance difficult. We propose Infini Memory, a maintainable text-based persistent memory architecture that treats agent memory as topic-structured documents. Each topic document serves as a semantic unit for collecting related evidence, preserving metadata, and revising facts over time. New observations are first staged in a buffer and periodically consolidated into coherent textual contexts. At inference time, an agentic retrieval procedure lets the LLM read memory through iterative tool calls rather than a single retrieval step. On MemoryAgentBench, Infini Memory achieves 64.7% overall score. Ablations show that topic-structured maintenance and iterative evidence inspection improve complementary aspects of long-term memory use.

Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-modal and temporal alignments at inference time, when context is limited and attribution is difficult. We propose EM^2Mem, an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors during memory construction. Each event-indexed memory cell aligns multimodal records, temporal context, graph-linked relations, semantic facts, and provenance, enabling compact evidence readout over grounded multimodal events rather than modality-specific fragments. Across three long-video QA benchmarks, EM^2Mem improves average accuracy over the strongest memory baseline by 2.0, 2.4, and 3.7 points, improves strict event-level Top-5 evidence recall by 7.0 points, and reduces per-query latency by 4.67 times and total inference tokens by 63.66% (The code will be integrated into https://github.com/zjunlp/LightMem).

LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only whether harmful actions can be prevented--it is whether those actions remain answerable after deployment. We distinguish accountability (the ability to determine compliance and assign responsibility), auditability (the system property that makes accountability possible), and auditing (the process of reconstructing behavior from trustworthy evidence). Our claim is direct: no agent system can be accountable without auditability. To make this operational, we define five dimensions of agent auditability, i.e., action recoverability, lifecycle coverage, policy checkability, responsibility attribution, and evidence integrity, and identify three mechanism classes (detect, enforce, recover) whose temporal information-and-intervention constraints explain why, in practice, no single approach suffices. We support the position with layered evidence rather than a single benchmark: lower-bound ecosystem measurements suggest that even basic security prerequisites for auditability are widely unmet (617 security findings across six prominent open-source projects); runtime feasibility results show that pre-execution mediation with tamper-evident records adds only 8.3 ms median overhead; and controlled recovery experiments show that responsibility-relevant information can be partially recovered even when conventional logs are missing. We propose an Auditability Card for agent systems and identify six open research problems organized by mechanism class.

Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying when evidence becomes valid, how visual history is maintained, or how responses are triggered. As a result, similar scores may correspond to different workloads, failure modes, and operational behavior. We introduce TRACE (Temporal Audit and Condition-aware Evaluation), a condition-aware benchmark and evaluation framework that makes these factors explicit. TRACE combines temporally audited visual tasks with evidence timing and instruction-dependent trigger annotations, a unified causal Core--Adapter protocol that controls information availability while recording actual history processing and response events, and multidimensional reporting of answer quality, timeliness, response-selection behavior, workload, completion, and reliability. On 1,240 records from 517 videos, we evaluate eight publicly available models or systems in eight configurations. We find that nearly identical QA accuracy can mask substantial differences in completion, answer validity, and generation workload, while proactive performance separates into response quality, response delay, false alarms (responses emitted while no target window is currently valid and a later one remains), and missed target windows. These results show that streaming-video performance should be interpreted as execution-conditioned system behavior rather than a single score. Our benchmark and code can be accessed at https://github.com/om-ai-lab/trace-bench{https://github.com/om-ai-lab/trace-bench}.

Real-world time-series forecasting is rarely a one-shot model invocation: practitioners must formulate tasks, connect data and models, incorporate domain expertise, assess prediction plausibility, and communicate uncertainty. Specialized forecasting models provide strong numerical predictions but usually operate in fixed pipelines, while general-purpose large language model (LLM) agents often lack forecasting-specific checks, constraints, and stopping rules. We present CastClaw, a human-in-the-loop autonomous forecasting system built through forecasting-oriented harness engineering. CastClaw connects data, specialized models, analytical tools, user input, and a versioned execution record in one runtime. Users specify the target, horizon, constraints, and hypotheses in natural language. Starting from a supplied or model-generated forecast, CastClaw checks temporal patterns and user constraints; when evidence is missing, it retrieves context, runs an analysis or another model, or asks the user. It then keeps, revises, or escalates the result under explicit stopping conditions. The output contains the final forecast and an execution report recording inputs, evidence, actions, and revisions. In this five-dataset electricity-price setting, CastClaw reports the lowest point-estimate MSE and MAE among 16 baselines. A Nord Pool case demonstrates the inspectable workflow. CastClaw was also validated offline on provincial electricity-load data from North China covering January--June 2026.

Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video accuracy conflates failures of local perception with failures to preserve observation identity, establish correspondence, and compose evidence, obscuring whether local video understanding actually transfers. We introduce EgoGears, a complementary single- and multi-video benchmark designed to diagnose this transition. It contains 567 single-video and 1,487 multi-video questions derived from 126 human-collected egocentric recordings covering 39 outdoor routes. Repeated traversals across movement speeds and lighting conditions ground comparisons in shared physical environments; 531 questions require alignment across independent recordings. Single-video questions measure the local visual, spatial, and motion evidence available to a model, while multi-video questions test whether evidence remains bound to the correct observation and can be composed into consistent route relationships. We report 29 single-video and 31 multi-video MLLM configurations across six model families in the main leaderboard. Among the 20 configurations evaluated comparably on both splits, every model performs worse on multi-video questions, with a mean decrease of 22.5 percentage points, and the gap persists when answer format and scoring are held fixed. The gap is not explained simply by additional videos or recording boundaries. The central bottlenecks are observation--evidence binding and ordered route-state tracking. The code and benchmark are publicly available at https://github.com/lei-qi-233/EgoGears.

Recent research in the field of reflexive metrics have studied the emergence and consequences of evaluation gaps in science. The concept of evaluation gaps captures potential discrepancies between what researchers value about their research, in particular research quality, and what metrics measure. As a result, scientists may experience anomie and adopt innovative ways to cope. These often value quantity over quality and may even compromise research integrity. A consequence of such gaps may therefore be research misconduct and a decrease in research quality. In the language of rational choice theory, an evaluation gap persists if motivational factors arising out of the internal component of an actors situation are incongruent with those arising out of the external components. The aim of this research is therefore to study and compare autonomous and controlled motivations to become an astronomer, to do research in astronomy and to publish scientific papers. Moreover, we study how these different motivational factors affect publication pressure, the experience of organisational justice and the observation of research misconduct. In summary, we find evidence for an evaluation gap and that controlled motivational factors arising from evaluation procedures based on publication record drives up publication pressure, which, in turn, was found to increase the likelihood of perceived frequency of misbehaviour.

LLM agents often retry after external validation rejects a candidate, but the interface between validation and the next model call remains underspecified. We introduce VeriHarness, a code-controlled agent loop in which models generate candidates while external validators control acceptance, budgets, and traces. We use it to compare raw diagnostics with feedback that identifies the failure location, observed value, and admissible alternatives. Across 50 paired TextWorld games under a four-call cap, feedback containing all three fields raises terminal success from 14/50 to 36/50 for Qwen2.5-Coder-14B (+44 percentage points) and from 8/50 to 29/50 for Llama-3.1-8B (+42 points). Ablations locate most of the gain in the admissible alternatives: feedback containing only the location and observed value remains near the raw diagnostic baseline. Presenting the complete repair information in prose instead of a keyed JSON record yields nearly the same success, providing no evidence that JSON syntax itself improves repair. The ordering persists across the tested call budgets and one sampled-decoding setting.

In this paper we introduce a new publicly available dataset for verification against textual sources, FEVER: Fact Extraction and VERification. It consists of 185,445 claims generated by altering sentences extracted from Wikipedia and subsequently verified without knowledge of the sentence they were derived from. The claims are classified as Supported, Refuted or NotEnoughInfo by annotators achieving 0.6841 in Fleiss kappa. For the first two classes, the annotators also recorded the sentence(s) forming the necessary evidence for their judgment. To characterize the challenge of the dataset presented, we develop a pipeline approach and compare it to suitably designed oracles. The best accuracy we achieve on labeling a claim accompanied by the correct evidence is 31.87%, while if we ignore the evidence we achieve 50.91%. Thus we believe that FEVER is a challenging testbed that will help stimulate progress on claim verification against textual sources.

LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it difficult to evaluate agents against evolving workflow demand or verify whether a task was executed. We introduce Claw-Eval-Live, a live benchmark for workflow agents that separates a refreshable signal layer, updated across releases from public workflow-demand signals, from a reproducible, time-stamped release snapshot. Each release is constructed from public workflow-demand signals, with ClawHub Top-500 skills used in the current release, and materialized as controlled tasks with fixed fixtures, services, workspaces, and graders. For grading, Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts, using deterministic checks when evidence is sufficient and structured LLM judging only for semantic dimensions. The release contains 105 tasks spanning controlled business services and local workspace repair, and evaluates 13 frontier models under a shared public pass rule. Experiments reveal that reliable workflow automation remains far from solved: the leading model passes only 66.7% of tasks and no model reaches 70%. Failures are structured by task family and execution surface, with HR, management, and multi-system business workflows as persistent bottlenecks and local workspace repair comparatively easier but unsaturated. Leaderboard rank alone is insufficient because models with similar pass rates can diverge in overall completion, and task-level discrimination concentrates in a middle band of tasks. Claw-Eval-Live suggests that workflow-agent evaluation should be grounded twice, in fresh external demand and in verifiable agent action.

Video understanding is shifting from the offline paradigm -- taking a fully recorded video as input and producing a single answer after it ends -- toward real-time interaction, in which the model perceives new frames while still replying, revises its answer as new evidence appears, and remains silent when there is nothing to say. We present MOSS-Video-Preview to validate this paradigm. Our central claim is that perception must not be blocked by generation; its natural realization is a two-channel architecture. We argue that a cross-attention backbone is better suited to real-time vision-language fusion than the prevailing decoder-only design: visual features enter through a side channel rather than joining the autoregressive sequence, so perception and generation run on separate, non-blocking pathways -- reducing the frequency of visual processing and exposing a clean channel-wise interface for independent compression. We complement this with a data synthesis pipeline that converts dense captions into real-time understanding QA whose answers are revised to match what the model has perceived so far, and we specialize an offline model on these data to elicit real-time behavior. Our model trails the strong Qwen2.5-VL-7B baseline overall -- a gap we attribute primarily to data and scale rather than the architecture -- yet attains competitive offline video and multimodal understanding, remains robust on the spatial and fine-grained temporal reasoning central to real-time use, and acquires behaviors that offline models lack: continuous perception, answer revision, and timely silence. On a single H200 with 256 frames per video, it achieves about a 5x speedup in time to first token and 2.7x higher decoding throughput, with negligible degradation in offline ability. Our study of paradigm, architecture, and data outlines a viable path toward real-time video understanding.

Inverse materials design starts from target functionality and searches for structures that can realize it. Its value in closed-loop discovery depends not only on prediction performance, but also on whether expensive first-principles results are independently validated, provenance-recorded, and admitted as feedback only when evidence is sufficient. This is especially important for composite properties such as carrier mobility, where a final scalar value hides intermediate quantities, fit quality, convergence history, and workflow assumptions. Here we present InvDesMobility, a reliability-gated first-principles feedback framework that integrates multi-agent automated DFT, evidence stratification, generative structure proposal, acquisition ranking, and auditable release. Using 516 2DMatPedia-derived candidates, the workflow produced 280 QC-passed materials and 573 retained carrier-direction seed channels after channel-level reliability gating. These records were split into two feedback objects: relaxed structures updated the generative model, while retained mobility channels trained the acquisition model and set validation priority. Over multiple iterations, InvDesMobility screened 2.4 x 10^6 structures, submitted 102 candidates for DFT validation, and retained 86 reliability-gated generated channels across 41 formulas. Overall, the main contribution is not a fixed list of high-mobility materials, but a transferable feedback contract that makes closed-loop inverse design both useful and auditable when learning from expensive calculated properties. All source data, retained feedback records, and workflows are available at https://github.com/DreamLufei/invDesMobility, with an accompanying evidence website at https://dreamlufei.github.io/invDesMobility/.

Electroencephalography (EEG) analysis extends beyond assigning predefined labels to recordings; it requires workflows connecting natural-language instructions, signal processing, quantitative evidence, and scientific interpretation. We term this capability comprehensive EEG understanding. Existing evaluations, however, primarily target isolated decoding tasks or system-specific demonstrations, leaving the competence of large language models (LLMs) insufficiently quantified. We introduce , a unified benchmark for comprehensive, instruction-conditioned EEG understanding. It comprises four subsets---Foundational Analysis, Sleep Assessment, Neurocognitive Assessment, and Physiological Integration---covering 17 datasets, tasks, and over real-data instances. Given an instruction and EEG recordings with optional physiological signals, a system must perform the analysis and produce a scientifically grounded report and, when required, artifacts. Outputs are assessed through numerical, categorical, set, sequence, semantic, and artifact validation. We evaluate representative LLMs across more than 100K executions under two paradigms: autonomous code execution with CodeAct and structured agentic analysis with BrainAgent. Results vary substantially across models, subsets, difficulty levels, and execution paradigms, showing that EEG competence depends on the model and its operationalization. provides a reproducible testbed for advancing LLM-based EEG understanding. The code and benchmark will be released soon, with evaluation results continuously updated.

Planetary geology relies on historical, interpretive reasoning to reconstruct past events from diverse observations. Here, we present a step toward an automated "machine intelligence geologist" by embedding this distinct methodology of geologic knowledge discovery and inference into a multimodal vision-language architecture. Focusing on the stratigraphy of lunar basaltic mare volcanism, we train a model to generate verifiably grounded geologic interpretations directly from co-registered topographic, spectral, and geologic maps. We demonstrate that while the system successfully balances established geological priors with local visual evidence to accurately describe stratigraphy and terrain, numeric age dating derived solely from vision defaults to memorized priors. Integrating an open-book retrieval mechanism resolves this, enabling the model to faithfully cite published chronologies. Our findings delineate the necessary architecture for automated geologic inference: site evidence must be visually interpreted from local data, while quantitative historical context must be retrieved from the scientific record.

WANDR (Wide ANd Deep Research) is a benchmark of 500 realistic, challenging data-collection tasks for research agents. Each task requires a system to discover a large set of entities that satisfy specified criteria (breadth), investigate each entity through multiple coordinated web searches (depth), and return independently verifiable records with supporting sources and excerpts. Tasks are represented as qualification key hierarchies that specify the entities, relationships, evidence, and required count at each level; a hierarchy with n companies, m employees per company, and k sources per employee requires n x m x k records. This structure supports diverse workflows such as market mapping, due diligence, literature review, product comparison, and talent sourcing, with targets ranging from dozens to thousands of records. WANDR replaces static gold answer sets with task-specific judges that refetch cited pages and verify each record against its evidence, allowing evaluation of current and changing facts. Record verdicts are aggregated into soft and hard precision, recall, and F1 scores that distinguish factual quality, coverage, and hierarchical completeness. The tasks are derived from de-identified product-usage logs and produced through a semi-automated pipeline with automated checks, empirical audits, and human review where needed. We evaluate six production research systems and find that the benchmark is far from saturated: at high effort, the strongest system reaches only 0.363 soft F1 and 0.133 hard F1. Performance degrades as target volume and hierarchy depth increase, with incomplete discovery, missing enrichment, and incomplete evidence construction remaining major bottlenecks. The benchmark and evaluation harness are available at https://github.com/perplexityai/wandr.

As code generation is increasingly delegated to AI systems, the bottleneck is shifting from writing code to supervising the systems that write it --- a shift CS-education researchers have begun to name. This shift exposes a vocabulary gap: the field asks for "human oversight" without a working distinction between the two things language does in a delegation channel --- coordinate action (cybernetic: words succeed when the world comes to match them) and coordinate understanding (epistemic: they succeed when they answer to the world and a hearer can check that they do). The failure this names is not cybernetic language but epistemic-form language doing cybernetic work: explanation-shaped output calibrated for approval rather than truth. Oversight that checks only whether an output was approved is satisfiable by rubber-stamping; oversight that holds an agent accountable requires the reasoning behind its work be retrievable and checkable. We present three delegation episodes --- illustrations, not controlled evidence --- in which epistemic engagement proved practicable while remaining auditable, one public record where a recommendation was withdrawn on its own stated terms, and one failure case illustrating oversight that requires no reasons for its discretionary choices. We propose a criterion for agentic-system governance, alongside existing technical trust properties: every consequential choice should carry the condition under which it would have gone otherwise, in a form a third party can test. Without such a condition, a third party cannot distinguish a decision from a rubber stamp. We give the criterion an operational form --- a two-part reconstruction test scoring a delegation record by whether a second reader can predict what the agent does under a perturbation --- and a deliberation-recording convention, ORRCF, that makes the condition a required component of every recorded choice.

Medical coding is essential for standardizing clinical data and communication but is often time-consuming and prone to errors. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label space, lengthy text inputs, and the absence of supporting evidence annotations that justify code selection. Recent advancements in Generative Artificial Intelligence (AI) offer promising solutions to these challenges. In this work, we introduce MedCodER, a Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. MedCodER achieves a micro-F1 score of 0.60 on International Classification of Diseases (ICD) code prediction, significantly outperforming state-of-the-art methods. Additionally, we present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts (https://doi.org/10.5281/zenodo.13308316). Ablation tests confirm that MedCodER's performance depends on the integration of each of its aforementioned components, as performance declines when these components are evaluated in isolation.

Despite substantial progress in fact-verification benchmarks, claims grounded in large-scale structured data remain underexplored. In this work, we introduce ClaimDB, the first fact-verification benchmark where the evidence for claims is derived from compositions of millions of records and multiple tables. ClaimDB consists of 80 unique real-life databases covering a wide range of domains, from governance and healthcare to media, education and the natural sciences. At this scale, verification approaches that rely on "reading" the evidence break down, forcing a timely shift toward reasoning in executable programs. We conduct extensive experiments with 30 state-of-the-art proprietary and open-source (below 70B) LLMs and find that none exceed 83% accuracy, with more than half below 55%. Our analysis also reveals that both closed- and open-source models struggle with abstention -- the ability to admit that there is no evidence to decide -- raising doubts about their reliability in high-stakes data analysis. We release the benchmark, code, and the LLM leaderboard at https://claimdb.github.io .

Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a cache of prior conversations. It should serve as a continuity and governance substrate: preserving durable user state, grounding answers in multimodal and device evidence, supporting correction and forgetting, bounding policy evolution, and remaining deployable under latency, cost, privacy, and edge-cloud constraints. This technical report presents Mi-Memory, a lifecycle memory framework for Personal AI organized around four roles: Structure, Expansion, Evolution, and Deployment. A shared audit contract links these roles through four recurring artifact families: typed evidence payloads preserve source identity and provenance, diagnostic traces localize evidence loss across the serving pipeline, strategy artifacts make memory-policy changes explicit, and gate/rollback records bound accepted evolution. MiMemory instantiates the roles through MemStack, MemSense/MemFuse, D^{2}ACCI/E^{2}MEND, and LiteMem. In controlled-reference Structure evaluations, MemStack reaches 93.59%, 57.24%, and 87.47% on LoCoMo, PersonaMem-V2, and LongMemEval, respectively; other tracks report module-level, preliminary/internal, transfer-feasibility, or design-only evidence with explicit boundaries. MiMemory is a step toward auditable, evidence-gated, and deployment-aware memory systems for Personal AI. Project homepage: https://darwin-agent.github.io/Mi-Memory/ .

Memory is central to long-horizon LLM agents, yet existing memory systems primarily preserve interaction content rather than modeling which agents can be trusted and under what conditions. This limitation is particularly important in multi-agent systems, where a central model may be unable to directly verify plausible or correlated peer responses. We introduce Σ-Mem, an online reliability memory that records historical competence evidence for individual peers and peer relationship evidence across the peer set. Both forms of evidence are maintained as real symmetric states and updated from post-decision correctness feedback. By Weyl's inequality, the spectral change caused by each event-level update is bounded, enabling stable online adaptation without retraining the underlying models. Σ-Mem provides a general write-and-read interface: the same memory can be used for residual steering of a central model, response-free peer routing, or reliability-weighted voting. Across five Qwen-family models, Σ-Mem adapts to counterfactual reliability shifts and generalizes to unseen peers and task domains. Direct memory readouts also outperform majority voting and the best fixed peer over the full OOD evaluation set. Moreover, performance improves consistently as more correctness feedback becomes available, indicating that Σ-Mem progressively accumulates actionable reliability information. These results establish reliability memory as a reusable foundation for adaptive coordination in LLM-based multi-agent systems.

Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, databases, clinical records, and formulary tools. Standard factuality metrics usually test whether an answer is supported by pooled evidence, missing a provenance-sensitive failure mode: a claim may be supported somewhere while being attributed to the wrong source. We call this cross-source conflation. We introduce ProvenanceGuard, a source-aware verifier for MCP-grounded answers. It consumes captured MCP traces with stable tool IDs, source IDs, and raw outputs; decomposes answers into atomic claims; routes claims to source-specific evidence; checks support with NLI and a token-alignment proxy; compares stated attribution with the routed source; and returns per-claim verdicts plus an answer-level allow/block decision. Blocked answers can be repaired with retrieval-augmented answer revision and re-verified. We evaluate on 281 medical-domain MCP-agent traces. A 266-trace adjudicated subset yields 2,325 LLM-assisted claim labels split by trace; 361 held-out labels are human-verified. On the 40-trace held-out split, ProvenanceGuard achieves block F1 0.802 and source accuracy 0.858 over 260 source-eligible claims, outperforming source-blind baselines that do not emit claim-to-source IDs. On a harder multi-source benchmark it reaches block F1 0.846, while source-plus-relation accuracy drops to 0.229, showing that exact source ownership remains difficult with semantically close sources. Repair-and-reverify resolves all blocked answers in the full trace set, often via conservative fallback. In 50 controlled clinical conflation probes, ProvenanceGuard detects all injected attribution swaps with no retained wrong attribution. These results show that source attribution is an independent axis for factuality verification in MCP-based agents.

Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the agent must rediscover these relationships for every query, often missing complementary evidence while simultaneously consuming substantial additional tokens. To address this, we introduce CorpusMap, a navigation layer that organizes the corpus around its recurring entities, which are identifiable from the documents themselves and can link a single document to many others across sources. Specifically, CorpusMap represents each recurring entity as an Entity Page that aggregates information about it and links to every document that refers to it, forming a graph between entities and documents that the agent can traverse to gather otherwise disconnected evidence. Moreover, since CorpusMap is constructed offline by resolving mentions of the same entity across documents, its links are shared across queries rather than rediscovered repeatedly at inference time. Using 7 different models with 3 benchmark datasets, we show that CorpusMap improves both evidence discovery and answer quality over raw-corpus agentic search while using fewer tokens on average, and further outperforms 4 alternative navigation layers, suggesting that entities serve as effective anchors for navigating large document collections.

Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Existing context-management methods make such rollouts feasible by truncating distant history, folding past turns into summaries, or selecting compact memory states. However, these breakthroughs introduce two coupled limitations. First, as the number of turns grows, historical observations are progressively removed or collapsed into compressed states, making it harder for the policy to reuse fine-grained evidence. Second, once the original turns are no longer source-addressable, outcome-based RL loses an explicit path for aligning policy updates with the evidence that supported a successful final answer. To this end, we propose ECHO, a selective turn-memory framework that jointly addresses history collapse and traceable learning through source-indexed reconstruction. Specifically, ECHO compresses each completed environment turn into a compact memory record, reconstructs bounded policy contexts by selecting from these records, and reuses the selected source indices to route positive outcome credit to the evidence and selection actions that support successful answers. On BrowseComp-Plus, ECHO reaches 43.4% held-out accuracy, outperforming GRPO (28.9%) and the rolling-summary baseline SUPO (36.1%), while using fewer turns and lower trajectory volume than SUPO (Figure 1). Additionally, the trained policy improves zero-shot generalization across multi-objective QA, code generation, and deep information-seeking benchmarks on both dense and MoE backbones.

This tutorial paper provides a step-by-step, reproducible walkthrough of NeuraDock Agent, an open-source EEG agent focused on Alpha dynamics and visual cognitive-load analysis. The goal is practical: a reader should be able to install the agent, run EEG preprocessing and quality control, generate Alpha dynamics figures, perform within-subject Rest/Task visual cognitive-load comparison, run the public mini-dataset analyses and compare them with the reference validation summary, start an online dashboard, call the real-time API from an external application, and use the LLM interpretation layer to explain quality risks. Existing EEG toolkits provide excellent offline analysis, but assembling a real-time, quality-gated cognitive-load pipeline often requires manually bridging acquisition, custom QC, Alpha feature extraction, and a web API; this tutorial closes that offline-to-online gap. The tutorial uses a quality-gated workflow: downstream Alpha and workload metrics are computed only after preprocessing and QC gating rather than directly from raw EEG. In the included mini-dataset validation, the agent processed 18 recordings, generated 10 within-subject comparisons, observed task-related posterior Alpha suppression in 7 of 10 contrasts, estimated initial evidence of within-subject repeatability, and benchmarked local online API latency. The tutorial is intended for researchers, developers, and applied teams who want a transparent path from EEG files to real-time visual cognitive-load prototypes.

Autonomous research systems are often evaluated as one-shot paper generators: given a topic, they produce a manuscript and a small set of experiment logs. This framing hides the operational problem that makes such systems difficult to trust: research is long-running, branching, failure-prone, and dependent on auditable handoffs between agents and humans. XScientist is a git-like research protocol and operating system for this setting. It orchestrates idea generation, experiment execution, manuscript drafting, self-review, repair, quality gating, daemon scheduling, and reproducibility artifacts as one continuously observable pipeline. The central design choice is to treat each run as a portable research artifact rather than only as a PDF. XScientist exports an Agent-Native Research Artifact (ARA), a protocol that records an exploration DAG, per-node code and outputs, claim-to-evidence anchors, content hashes, provenance, and re-execution hooks. This makes each generated paper inspectable as a science exploration tree: failed branches, repaired experiments, ablations, and manuscript claims remain connected to the nodes that produced them. The system also includes deterministic integrity forensics, sample gates, truth contracts, reviewer-oriented repair loops, and long-running daemon controls. This paper describes the current XScientist architecture, the ARA protocol surface, and the practical safeguards needed to move autonomous science from single-run demos toward reproducible, reviewable, and forkable research infrastructure. The implementation and manuscript source are maintained in the public GitHub repository at https://github.com/smileformylove/XScientist.

Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed, what changed, or why a regression occurred. This is not a generation failure but a control failure: the dominant artifact of AI-assisted development (code plus chat history) performs dimension collapse, flattening complex system topology into low-dimensional text and making systems opaque and fragile under change. We propose Agentic Consensus: a paradigm in which the consensus layer C, an operable world model represented as a typed property graph, replaces code as the primary artifact of engineering. Executable artifacts are derived from C and kept in correspondence via synchronization operators Phi (realize) and Psi (rehydrate). Evidence links directly to structural claims in C, making every commitment auditable and under-specification explicit as measurable consensus entropy rather than a silent guess. Evaluation must move beyond code correctness toward alignment fidelity, consensus entropy, and intervention distance. We propose benchmark task families designed to measure whether consensus-based workflows reduce human intervention compared to chat-driven baselines.

Metric differential privacy (mDP) strengthens local differential privacy (LDP) by scaling noise to semantic distance, but many machine learning (ML) systems are consumed under joint observation, where model-agnostic, per-record guarantees can miss leakage from evidence aggregation. We introduce metric-normalized posterior leakage (mPL), an attacker-aligned, distance-calibrated measure of posterior-odds shift induced by releases, and show that for single or independent releases, uniformly bounding mPL is equivalent to mDP. Under joint observation, however, satisfying mDP may still leave mPL high because learned aggregators compound evidence across correlated items. To make control practical, we formalize probabilistically bounded mPL (PBmPL), which limits how often mPL may exceed a target budget, and we operationalize it via Adaptive mPL (AmPL), a trust-and-verify framework that perturbs, audits with a learned attacker, and adapts parameters (with optional Bayesian remapping) to balance privacy and utility. In a word-embedding case study, neural adversaries violate mPL under joint consumption despite per-record mDP perturbations, whereas AmPL substantially lowers the frequency of such violations with low utility loss, indicating PBmPL as a practical, certifiable protection for joint-consumption settings.

AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers cannot reliably compare results across sources, identify what a report omits, or trace an aggregate claim to its underlying evidence. Recent efforts address isolated components but leave three gaps: they cover only narrow slices of the evaluation lifecycle and do not compose into a single interpretable record; they specify static representations that do not differentiate the questions different stakeholders bring to the same evidence; and they remain proposals on paper, lacking the extraction infrastructure required for adoption at scale. We present , an operational reporting layer that composes benchmark metadata, evaluation run data, and model metadata into a unified record. We (1) derive a reporting schema from a structured review of 52 papers and 10 stakeholder interviews, (2) implement four interpretive signals (reproducibility, documentation completeness, provenance and risk, and score comparability), rendered through reader modes calibrated to research and non-research audiences, and (3) deploy a monitoring tool that applies across 5,816 models, 635 benchmarks, and 101,843 results, surfacing systematic gaps in current reporting practice.

Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Bench), a benchmark for scientific lineage reasoning and lineage-grounded idea generation. IG-Bench is organized around the IdeaGene framework: each paper or proposal is represented as a set of minimal, typed, evidence-grounded Idea Genome objects, and a GenomeDiff aligns these objects to record inheritance, mutation, loss, external import, and novel insertion under six operational evolutionary dynamics. The benchmark contains 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise GenomeDiff records across 10 scientific domains. It supports two evaluations. IG-Exam (42 task types, 1,029 instances) tests closed-form lineage reasoning across Idea Genome abstraction, inheritance tracing, evolutionary reasoning, and lineage verification. IG-Arena evaluates generation with a lineage-conditioned Population-Evolution Score(PES), asking whether a proposal can be inserted as a coherent descendant of a given lineage population: it should inherit the right Idea Genome objects, vary meaningfully from nearby work, and offer selection value for future research. Experiments on 14 LLM-based scientists expose a compositional bottleneck. The strongest system reaches only 27.3% exact accuracy on lineage reasoning, and structured lineage context reshuffles system rankings rather than helping every participant uniformly.

Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks. Existing evaluations largely examine clean learning or perturbations encountered after skills are frozen, leaving robustness during self-evolution insufficiently understood. We introduce RSE-Bench, to our knowledge the first benchmark for evaluating skill self-evolution under ordinary, non-adversarial noise. It spans four domains and six benchmarks, with controlled perturbations to instructions, environmental evidence, execution records, and outcome--record pairings that preserve the underlying tasks and native scoring rules. The protocol separates noise during learning from input-side noise at evaluation, testing frozen skill stores on held-out tasks. We also introduce RSEClaw, a method-agnostic framework supporting consistent noise injection and process diagnostics of actual exposure and skill updates. Across three methods and two backbones, noisy learning retains only 25.5%--42.1% of the aggregate gain achieved by clean self-evolution, depending on the noise type. Perturbations confined to execution records and outcome--record pairings cause average losses comparable to input-side noise, despite leaving the original executions and evaluations intact. Diagnostics further identify differences in candidate skill text that coexist with small changes in mean held-out performance.

In medieval India, the Marathi language was written using the Modi script. The texts written in Modi script include extensive knowledge about medieval sciences, medicines, land records and authentic evidence about Indian history. Around 40 million documents are in poor condition and have not yet been transliterated. Furthermore, only a few experts in this domain can transliterate this script into English or Devanagari. Most of the past research predominantly focuses on individual character recognition. A system that can transliterate Modi script documents to Devanagari script is needed. We propose the MoDeTrans dataset, comprising 2,043 images of Modi script documents accompanied by their corresponding textual transliterations in Devanagari. We further introduce MoScNet (Modi Script Network), a novel Vision-Language Model (VLM) framework for transliterating Modi script images into Devanagari text. MoScNet leverages Knowledge Distillation, where a student model learns from a teacher model to enhance transliteration performance. The final student model of MoScNet has better performance than the teacher model while having 163times lower parameters. Our work is the first to perform direct transliteration from the handwritten Modi script to the Devanagari script. MoScNet also shows competitive results on the optical character recognition (OCR) task.

Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change independently of the agent: new emails arrive, calendar entries shift, knowledge-base records are updated, and evidence appears across images, scanned PDFs, audio, video, and spreadsheets. Existing benchmarks do not adequately evaluate this setting because they typically run within a single static episode and remain largely text-centric. We introduce , a benchmark for coworker agents built around multi-turn multi-day tasks, a stateful sandboxed service environment whose state evolves between turns, and rule-based verification. The current release contains 100 tasks across 13 professional scenarios, executed against five stateful sandboxed services (filesystem, email, calendar, knowledge base, spreadsheet) and scored by 1537 deterministic Python checkers over post-execution service state; no LLM-as-judge is invoked during scoring. We benchmark seven frontier agent systems. The strongest model reaches 75.8 weighted score, but the best strict Task Success is only 20.0\%, indicating that partial progress is common while complete end-to-end workflow completion remains rare. Turn-level analysis shows that performance drops after the first exogenous environment update, highlighting adaptation to changing state as a key open challenge. We release the benchmark, evaluation harness, and construction pipeline to support reproducible coworker-agent evaluation.

LLM agents increasingly rely on reusable skills, capability packages that combine instructions, control flow, constraints, and tool calls. In most current agent systems, however, skills are still represented by text-heavy artifacts, including SKILL.md-style documents and structured records whose machine-usable evidence remains embedded largely in natural-language descriptions. This poses a challenge for skill-centered agent systems: managing skill collections and using skills to support agent both require reasoning over invocation interfaces, execution structure, and concrete side effects that are often entangled in a single textual surface. An explicit representation of skill knowledge may therefore help make these artifacts easier for machines to acquire and leverage. Drawing on Memory Organization Packets, Script Theory, and Conceptual Dependency from Schank and Abelson's classical work on linguistic knowledge representation, we introduce what is, to our knowledge, the first structured representation for agent skill artifacts that disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action and resource-use evidence: the Scheduling-Structural-Logical (SSL) representation. We instantiate SSL with an LLM-based normalizer and evaluate it on a corpus of skills in two tasks, Skill Discovery and Risk Assessment, and superiorly outperform the text-only baselines: in Skill Discovery, SSL improves MRR from 0.573 to 0.707; in Risk Assessment, it improves macro F1 from 0.744 to 0.787. These findings reveal that explicit, source-grounded structure makes agent skills easier to search and review. They also suggest that SSL is best understood as a practical step toward more inspectable, reusable, and operationally actionable skill representations for agent systems, rather than as a finished standard or an end-to-end mechanism for managing and using skills.

Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which constraints remain open, and which claims have actually been checked. We argue that this formulation puts too much routine state management inside the policy: reinforcement learning is forced to optimize both semantic search decisions and recoverable bookkeeping that the environment can maintain more reliably. We introduce Harness-1, a 20B search agent (retrieval subagent) trained with reinforcement learning inside a stateful search harness. The harness maintains environment-side working memory, including a candidate pool, an importance-tagged curated set, compact evidence links, verification records, compressed and deduplicated observations, and budget-aware context rendering. The policy retains the semantic decisions: what to search, which documents to keep or discard, what to verify, and when to stop. Across eight retrieval benchmarks spanning web, finance, patents, and multi-hop QA, Harness-1 achieves 0.730 average curated recall, outperforming the next strongest open search subagent by +11.4 points and remaining competitive with much larger frontier-model searchers. Its gains are especially strong on held-out transfer benchmarks, suggesting that reinforcement learning over explicit search state can produce retrieval behaviors that generalize beyond the training domains. Our code is available at https://github.com/pat-jj/harness-1.

Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions. Static harnesses improve reliability through fixed tools, context, memory, and workflow structures, but remain unchanged after deployment. We propose Living-Harness, a self-evolving agent harness that converts each completed trajectory and its evaluator signals into posterior evidence for bounded harness updates. Guided by a domain-level Evolution-SOP (Standard Operating Procedure), Living-Harness extracts an episode abstraction and structured update evidence, and writes two complementary forms of procedural knowledge: episodic memory that records trigger conditions, failure patterns, and recovery actions, and a state graph that records state nodes, repair edges, and transition rules. The updated harness state is retrieved to guide future interactions, while tools and base context remain frozen, allowing procedural repairs to accumulate across evolution cycles. On eight interactive environments derived from τ^2-Bench and MultiWOZ-2.4, Living-Harness improves average Pass@1 over the strongest interactive baseline by 10.07 and 9.91 percentage points, respectively, and supports retrieval-only reuse of the evolved harness state across model backbones.

Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured. We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discriminative, and testable hypothesis spaces from inconclusive evidence, including anomalous observations and fragmented records, to guide subsequent investigation. To evaluate this capability, we introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets. To construct HypoData at scale, we propose Retrospective Context Regression, a Forge--Audit pipeline that reconstructs pre-conclusion contexts from completed expert documents by removing explicit conclusions, target hypotheses, and retrospective causal attributions while preserving the factual substrate. Because PHD admits multiple valid outputs, HypoEval combines bidirectional pairwise judgments with Bradley--Terry--Davidson aggregation for ranking and six-dimensional rubric scoring for diagnosis. Experiments on 15 frontier LLMs reveal clear capability stratification and model-dependent effects of structured analytical skills, with gains for several lower-performing models on HypoArena but regressions for other systems, including a top-performing model. Compared with absolute rubric scoring, arena evaluation resolves finer-grained differences among models, with aggregated rankings showing strong agreement with human experts and an independent judge. Together, these results support treating PHD as a distinct target for evaluating how LLMs formulate investigative directions when final conclusions are withheld. Our code and data are publicly available at github.com/SKYLENAGE-AI/HypoArena and github.com/SKYLENAGE-AI/HypoArena.

Coding agents such as Claude Code and Codex close the software loop: a main agent manages the loop, subagents analyze and execute, tools do the work. We port this architecture to robot-policy improvement, where one difference dominates the design: robotic tools---trained policies, training pipelines, data collection---fail routinely, so a tool's quality must be measured, recorded at every call, and expired when the artifact behind it changes. AgenticRobotics is a backend-independent control plane in which an LLM controller drives disposable workers through durable train--evaluate--improve transactions: an immutable objective, controller-owned measurement, commit-keyed crash recovery, an evidence-graded skill library, and a tool registry with a standardized, recorded call surface. The title is an operational claim, not a selection claim: the operator can leave because promotion is evidence-gated, state is recoverable, and capability quality is derived from records---not because the loop picks better checkpoints than a human; on the one lineage we measured, it does not. The gates measurably buy false-promotion control (0.001 per run hardened versus 0.005--0.021 shipped), anytime-valid decisions under optional stopping, zero lost or duplicate effects under kill injection, and six of six artifact-tampering classes caught by a signed verifier.

A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounded discretion, benchmarks score a label or a rubric, and the experience that would supply the balance stays unverified. We formalize legal judgment as a reference-anchored task, whose object is a single decision that stays tied to the statute and to the circumstances at once. We introduce JusticeAxis, 256 real-world criminal cases from 18 countries with audio, image, and text evidence, and three lawyer-written judgments for every case: the recorded one and one for each failure. We further propose JusticeAgent, a harness whose element agents establish the facts and whose judge agent applies the law under skills carrying experience of the circumstances. Skills are distilled from execution trajectories and admitted only under Bayesian credible bounds. Experiments show that failure turns direction with scale: open-weight backbones drift to unsupported grounds, frontier models to the statutory default. We further verify that JusticeAgent, as a simple yet effective plugin, carries a frozen open-weight backbone to commercial level. Project resources are available at https://github.com/beita6969/JusticeAxis.

Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adaptation method that keeps the model frozen and learns a single block of prompt vectors inserted at the decoder input, between the audio and question embeddings. We train these vectors through self-distillation over diverse audio and text perturbations. To improve answer consistency and mitigate hallucination, we use the model's prediction on the clean recording as the target for answerable inputs, and assign a refusal target when the audio lacks sufficient evidence to answer. Furthermore, AnchorPrompt is perturbation-agnostic at inference, requiring no prior detection of perturbations and enabling zero-shot transfer to unseen distortions. We evaluate three LALMs across three benchmarks and show that AnchorPrompt improves answer consistency in most tested conditions. Clean accuracy improves in six of nine model-benchmark pairs, with minimal impact on the remainder of 1.2% at most. Crucially, AnchorPrompt reduces hallucinations under severe audio corruption while keeping false refusals on clean audio rare. Finally, these consistency gains transfer to unseen perturbations, such as choice permutations and reverberation.

Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending agents beyond prior experience. Existing methods face two limitations: trajectory-based synthesis requires interactions with specific environments, while document-derived skills may lack executable evidence and verification. Source code offers a complementary path: it requires no prior agent experience yet provides executable evidence for grounding abstractions. We present Code2Skill, a fully automated pipeline that transforms selected code units into implementation-anchored records of atomic operations, composite workflows, and recurring patterns, then verifies each record through source-body-blind reconstruction and source-aware comparison. Applied to 19,769 popular, actively maintained GitHub repositories, Code2Skill produces CodeSkillBank, a grounded bank of 1,006,822 accepted records with workflow, boundary, provenance, and source-evidence metadata. Across 72 protocol-matched evaluations covering nine model settings and eight benchmarks, models augmented with retrieved CodeSkillBank skills improve by 11.7% on average over matched baselines and outperform them in 57 cases. Under a unified downstream interface, Code2Skill also outperforms trajectory-derived skill banks on all seven shared benchmarks, showing that repository-derived skills can provide useful procedural knowledge before agents accumulate sufficient interaction experience. Skills synthesized from tested AI-generated code achieve a 93.50% pass rate, compared with 93.00% for human-written code, providing initial evidence that the pipeline can expand with the growing volume of AI-generated software. Overall, Code2Skill transforms procedural knowledge embedded in repositories into grounded, verifiable, and transferable agent skills.

AI agents now hold spend authority and settle payments without per-action human confirmation. The resulting loss is often not a security failure: a counterparty with the correct domain, the correct settlement address and a genuinely delivered service can charge more than it should, and no check keyed on identity will see it. We present three artefacts for measuring and reducing that loss. First, a taxonomy of agentic commerce fraud that separates five observation levels (agent reasoning, wire, settlement rail, counterparty, principal) from the request-level and history-level evidence available at each, and records which levels can observe which attacks. Second, Agentic Commerce Bench (ACB), a benchmark of twenty fraud classes generated from production aggregates, 1,647 catalogued service operations and 1,068 settlements, of which six involve a counterparty that is exactly who it claims to be. Third, gordonguard, an open-source detector stack and offline harness with which an operator can audit an agent configuration, replay hostile counterparties without an account, and run the same detectors inline. Calibrating to a stated false-positive budget on clean training traffic gives a 6.5% clean flag rate, replicated across three independent generations, and leaves eight of twenty classes no better than chance. On the four classes a reasoning layer can observe, a widely used agent security scanner run over its jailbreak-detection panel scores zero on all four, while correctly scoring 1.0 on a jailbreak supplied as a control. A measured median payment of $0.007 places a hard constraint on deployment: one human review costs 143 times the value of the payment it examines.

Multi-agent LLM ensembles can converge on coordinated, socially harmful equilibria. This paper advances an experimental framework for evaluating Institutional AI, our system-level approach to AI alignment that reframes alignment from preference engineering in agent-space to mechanism design in institution-space. Central to this approach is the governance graph, a public, immutable manifest that declares legal states, transitions, sanctions, and restorative paths; an Oracle/Controller runtime interprets this manifest, attaching enforceable consequences to evidence of coordination while recording a cryptographically keyed, append-only governance log for audit and provenance. We apply the Institutional AI framework to govern the Cournot collusion case documented by prior work and compare three regimes: Ungoverned (baseline incentives from the structure of the Cournot market), Constitutional (a prompt-only policy-as-prompt prohibition implemented as a fixed written anti-collusion constitution, and Institutional (governance-graph-based). Across six model configurations including cross-provider pairs (N=90 runs/condition), the Institutional regime produces large reductions in collusion: mean tier falls from 3.1 to 1.8 (Cohen's d=1.28), and severe-collusion incidence drops from 50% to 5.6%. The prompt-only Constitutional baseline yields no reliable improvement, illustrating that declarative prohibitions do not bind under optimisation pressure. These results suggest that multi-agent alignment may benefit from being framed as an institutional design problem, where governance graphs can provide a tractable abstraction for alignment-relevant collective behavior.

Retrieval-enhanced methods have become a primary approach in fact verification (FV); it requires reasoning over multiple retrieved pieces of evidence to verify the integrity of a claim. To retrieve evidence, existing work often employs off-the-shelf retrieval models whose design is based on the probability ranking principle. We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence. We introduce the feedback-based evidence retriever(FER) that optimizes the evidence retrieval process by incorporating feedback from the claim verifier. As a feedback signal we use the divergence in utility between how effectively the verifier utilizes the retrieved evidence and the ground-truth evidence to produce the final claim label. Empirical studies demonstrate the superiority of FER over prevailing baselines.

We contribute the largest publicly available dataset of naturally occurring factual claims for the purpose of automatic claim verification. It is collected from 26 fact checking websites in English, paired with textual sources and rich metadata, and labelled for veracity by human expert journalists. We present an in-depth analysis of the dataset, highlighting characteristics and challenges. Further, we present results for automatic veracity prediction, both with established baselines and with a novel method for joint ranking of evidence pages and predicting veracity that outperforms all baselines. Significant performance increases are achieved by encoding evidence, and by modelling metadata. Our best-performing model achieves a Macro F1 of 49.2%, showing that this is a challenging testbed for claim veracity prediction.

International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis. Reliable coding requires that each predicted code be supported by explicit textual evidence. However, existing public datasets provide only code labels, without evidence annotations, limiting models' ability to learn evidence-grounded predictions. In this work, we argue that dense, document-level evidence annotation is not always necessary for learning evidence-based coding. Instead, models can learn code-specific evidence patterns from local spans and use these patterns to support document-level evidence-based coding. Based on this insight, we propose Span-Centric Learning (SCL), a training framework that strengthens LLMs' coding ability at the span level and transfers this capability to full clinical documents. Specifically, we use a small set of annotated documents to supervise evidence recognition, aggregation, and code assignment, while leveraging a large collection of lightweight evidence spans to reinforce span-level reasoning. Due to their compactness, span annotations are scalable and can be further augmented through synthesis. Under the same Llama3.1-8B backbone, our approach achieves an 8.2-point improvement in macro-F1 at only 20% of the training cost of standard SFT, and provides explicit supporting evidence for each predicted code, enabling human auditing and revision.

Long-running LLM agents compress past interactions into persistent memories that may be reused as premises for later tasks. This creates a distinct derivation problem: whether the memory actually follows from what the interaction history supports. Relevant evidence may be scattered across earlier interactions, while compression can introduce relations or event status that the history never established. A valid memory may therefore appear unsupported because its citations omit relevant evidence, while individually supported facts may be composed into a stronger statement the history never established. We characterize this problem through three coupled requirements: (1) Evidence scope; (2) Compositional validity; (3) Admission reliability. We therefore ask whether the interaction history available at write time supports what enters persistent memory. We introduce DerivAudit, a framework for auditing whether a memory is actually supported by the history available when it was written. The audit separates three questions: whether supporting evidence lies beyond writer-provided citations, whether the composed memory introduces unsupported meaning, and how write-time admission decisions affect later memory use. Across two natural memory corpora, audits using broader pre-write history recover support for nearly 60% of memories that appear unsupported from citations alone, while 17-21% remain unsupported after expansion. Yet broader evidence does not by itself make admission reliable: unsupported memories are still frequently admitted across verification models, and evidence expansion alone worsens it on two backbones.

Recent large language models often answer factual questions correctly. But users can't trust any given claim a model makes without fact-checking, because language models can hallucinate convincing nonsense. In this work we use reinforcement learning from human preferences (RLHP) to train "open-book" QA models that generate answers whilst also citing specific evidence for their claims, which aids in the appraisal of correctness. Supporting evidence is drawn from multiple documents found via a search engine, or from a single user-provided document. Our 280 billion parameter model, GopherCite, is able to produce answers with high quality supporting evidence and abstain from answering when unsure. We measure the performance of GopherCite by conducting human evaluation of answers to questions in a subset of the NaturalQuestions and ELI5 datasets. The model's response is found to be high-quality 80\% of the time on this Natural Questions subset, and 67\% of the time on the ELI5 subset. Abstaining from the third of questions for which it is most unsure improves performance to 90\% and 80\% respectively, approaching human baselines. However, analysis on the adversarial TruthfulQA dataset shows why citation is only one part of an overall strategy for safety and trustworthiness: not all claims supported by evidence are true.