new

Get trending papers in your email inbox!

Subscribe

Daily Papers

byAK and the research community

Nov 19

TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models

Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-specific annotations. Existing open-source VLM reward judges like RoboReward adopt simple 1--5 trajectory progress scoring, lacking pairwise preferences for RLHF, DPO and Bradley-Terry frameworks, while failing to optimize video scene understanding. Augmenting RoboReward with pairwise comparison and video-QA supervision causes inconsistency between pairwise preferences and pointwise scores, introducing training noise and hurting downstream performance---an issue aggregation methods such as TrustJudge cannot resolve. To address this, we propose TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE). We construct a unified four-paradigm dataset with trajectory progress scoring (Score-A), video-QA answer quality scoring (Score-B), and their pairwise counterparts (Pair-A, Pair-B). Pairwise labels align better with human judgment than pointwise scores, inspiring us to calibrate pointwise scores to avoid score-pair reversals against pairwise preferences. POISE rectifies pointwise scores and eliminates cross-paradigm reversal conflicts unresolved by TrustJudge. Theoretically, POISE reduces score-pair reversal conflicts from 20.15% to 0%, whereas TrustJudge retains 20.46% conflicts on the same corpus. Evaluated on our benchmark, Qwen3-VL-4B trained with POISE achieves an overall reward score of 77.96%, nearly matching GPT-5-mini (78.09%, gap 0.13%) and outperforming the strongest RoboReward-4B baseline by 10.13%. It also lifts test-time score-pair consistency to 71.90%, exceeding RoboReward-4B (57.26%) and GPT-5-mini (68.09%). Integrating TrustJudge aggregation during inference boosts the overall score to 78.57%, surpassing the GPT-5-mini teacher model.

  • 19 authors
·
Aug 8

AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluation

Millions of people now use generative AI chatbots for psychological support. Despite their promise, the most pressing question in AI for mental health is whether these tools are safe. The field currently lacks a validated, automated benchmark for evaluating AI chatbot safety, particularly for users at risk of suicide. The Validation of Ethical and Responsible AI in Mental Health (VERA-MH) evaluation was recently proposed to address this need. This human validation study examined the alignment of VERA-MH safety ratings with expert clinician judgments. We simulated conversations between large language model (LLM)-based users spanning a range of suicide risk levels and disclosure styles and general-purpose AI chatbots. Licensed mental health clinicians from Spring Health independently rated chatbot safety using the VERA-MH scoring rubric. An LLM-based evaluator ("judge") applied the same rubric to the same conversations. We examined agreement among clinicians, between clinician consensus and the LLM judge, and across different judge LLMs. Clinicians also rated user-agent realism, suicide risk, and disclosure. Clinicians showed strong agreement in safety ratings (chance-corrected inter-rater reliability [IRR] = 0.77), establishing a reliable clinical consensus reference. The LLM judge was strongly aligned with this consensus (IRR = 0.81), and ratings were stable across judge models and repeated evaluations. Ratings of user-agent realism and fidelity to intended suicide risk and disclosure styles were mixed. These findings support the reliability of VERA-MH as an open-source, fully automated benchmark for evaluating AI chatbot suicide risk detection and response. Because these results reflect an earlier version of the benchmark, future work should validate updated versions, assess generalizability and robustness, and expand VERA-MH to additional domains of AI safety in mental health.

  • 10 authors
·
Feb 4

Who judges the judges? Governance from metrics: a runtime framework for continuous LLM compliance monitoring

Current approaches to AI compliance treat conformity as a binary, audit-time verdict rather than a continuous, measurable property of production systems. We argue that this compliance fiction is structurally ill-suited to the requirements of the EU AI Act, which demands ongoing human oversight and the detection of emergent behavioural drift in deployed systems. We introduce governance from metrics, a principle whereby regulatory compliance is derived as a continuous signal from runtime observability rather than from static assessments. Building on this principle, we present govllm, an open-source framework implementing a governance-driven routing architecture in which model selection is determined by accumulated compliance scores rather than by latency or cost alone. Central to our approach is a panel of regulatory judges - LLM evaluators specialised per criterion (EU AI Act, GDPR, ANSSI, accessibility) - whose inter-judge disagreement we reframe not as noise but as a regulatory uncertainty signal warranting human arbitration. We validate this approach through a ground truth corpus of 49 annotated prompt/response pairs across five regulatory criteria, evaluated by four small language models (SLMs, 1.7B-7B parameters) running fully on-premise. Agreement rates range from 51.5% (mistral:7b) to 69.1% (phi4-mini), with no single model dominating across all criteria - empirically motivating the Profile-as-jury design. We further document three structural failure modes in small regulatory judges and a judge-specific position bias that degrades agreement by up to 25 percentage points across three question-order conditions (original, reversed, permuted). govllm is released as open-source software to support reproducible AI governance research.

  • 1 authors
·
May 22

Lost in Translation: Do LVLM Judges Generalize Across Languages?

Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision-language models (LVLMs). Despite their growing importance, these evaluators are almost exclusively assessed on English-centric benchmarks, leaving open the question of how well these evaluators generalize across languages. To answer this question, we introduce MM-JudgeBench, the first large-scale benchmark for multilingual and multimodal judge model evaluation, which includes over 60K pairwise preference instances spanning 25 typologically diverse languages. MM-JudgeBench integrates two complementary subsets: a general vision-language preference evaluation subset extending VL-RewardBench, and a chart-centric visual-text reasoning subset derived from OpenCQA, enabling systematic analysis of reward models (i.e., LVLM judges) across diverse settings. We additionally release a multilingual training set derived from MM-RewardBench, disjoint from our evaluation data, to support domain adaptation. By evaluating 22 LVLMs (15 open-source, 7 proprietary), we uncover substantial cross-lingual performance variance in our proposed benchmark. Our analysis further shows that model size and architecture are poor predictors of multilingual robustness, and that even state-of-the-art LVLM judges exhibit inconsistent behavior across languages. Together, these findings expose fundamental limitations of current reward modeling and underscore the necessity of multilingual, multimodal benchmarks for developing reliable automated evaluators.

  • 8 authors
·
Apr 20

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuring reliability and uncovering fine-grained model weaknesses. Since human evaluation is laborious and costly, prompting MLLMs as automated process judges has become a common practice. However, the reliability of these model-based judges remains uncertain. To address this, we introduce ProJudgeBench, the first comprehensive benchmark specifically designed for evaluating abilities of MLLM-based process judges. ProJudgeBench comprises 2,400 test cases and 50,118 step-level labels, spanning four scientific disciplines with diverse difficulty levels and multi-modal content. In ProJudgeBench, each step is meticulously annotated by human experts for correctness, error type, and explanation, enabling a systematic evaluation of judges' capabilities to detect, classify and diagnose errors. Evaluation on ProJudgeBench reveals a significant performance gap between open-source and proprietary models. To bridge this gap, we further propose ProJudge-173k, a large-scale instruction-tuning dataset, and a Dynamic Dual-Phase fine-tuning strategy that encourages models to explicitly reason through problem-solving before assessing solutions. Both contributions significantly enhance the process evaluation capabilities of open-source models. All the resources will be released to foster future research of reliable multi-modal process evaluation.

  • 11 authors
·
Mar 9, 2025 2

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences. However, their ability to follow diverse, fine-grained evaluation criteria remains underexplored. We develop Multi-Crit, a benchmark for evaluating multimodal judges on their capacity to follow pluralistic criteria and produce reliable criterion-level judgments. Covering both open-ended generation and verifiable reasoning tasks, Multi-Crit is built through a rigorous data curation pipeline that gathers challenging response pairs with multi-criterion human annotations. It further introduces three novel metrics for systematically assessing pluralistic adherence, criterion-switching flexibility, and the ability to recognize criterion-level preference conflicts. Comprehensive analysis of 25 LMMs reveals that 1) proprietary models still struggle to maintain consistent adherence to pluralistic criteria--especially in open-ended evaluation; 2) open-source models lag further behind in flexibly following diverse criteria; and 3) critic fine-tuning with holistic judgment signals enhances visual grounding but fails to generalize to pluralistic criterion-level judgment. Additional analyses on reasoning fine-tuning, test-time scaling, and boundary consistency between open-source and proprietary models further probe the limits of current multimodal judges. As a pioneering study, Multi-Crit lays the foundation for building reliable and steerable multimodal AI evaluation.

PlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?

Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models. Whether their judgments remain reliable when the evidence is buried in day-long videos has yet to be established. Existing benchmarks cannot answer this. Their videos are typically only a few minutes long, many answer pairs can be separated from the transcript alone, and collecting human judgments does not scale to ultra-long videos. We introduce PlaylistEval, an agentic framework that builds video-language judge benchmarks over 100-hour playlist collection without human annotation. It automatically generates questions with paired answers whose differences are controlled by causal degradation, so that every pair demands retrieval across the collection. The resulting benchmark contains 630 pairs across seven domains spanning both static and dynamic knowledge, and on a stratified subset of 152 pairs it agrees with human judgments 93.0% of the time (IAA 0.781). Evaluating 17 omnimodal and multimodal models from eight families reveals that frontier judges reach only 75.4% pairwise accuracy, while open-source judge models perform far behind. We further show that both retrieval and final judgment depend on using multiple modalities, and that judge accuracy degrades as the playlist set grows. We release our pipeline, benchmark, and evaluation code at https://playlisteval.github.io.

  • 2 authors
·
Sep 27 1

VisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision

Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them. Yet existing benchmarks score only scalar quality or overall preference, so a judge can be rewarded for picking the preferred image for the wrong visual reason. We introduce VisionQ, the first benchmark built from peer-reviewed CV comparison figures that grounds every judgment in a named visual criterion: each question states the criterion, and a judge is credited only when it selects the output the authors identify as best on that criterion. We call this task criterion-conditioned visual discrimination. VisionQ comprises (1) a corpus of 1,409 CVPR and ICCV papers with 1,800+ validated comparison figures and 3,911 hand-annotated data points linking method crops to author-stated visual claims; (2) a six-axis, 51-leaf taxonomy of the visual criteria behind qualitative judgment; (3) a criterion-conditioned evaluation protocol that hides method names, captions, and paper identity and reports accuracy per criterion; and (4) VisionQ-Judge, a DPO-tuned Gemma-4-E4B judge trained on symmetric evidence pairs, which reduces last-option predictions by 7.0pp and improves accuracy by 2.5pp on a held-out test set. Evaluating 20 open- and closed-source VLM judges, we find that the strongest reach only 63.1% accuracy (chance 32.2%) and that reliability varies sharply across criteria. Code: https://github.com/ReML-AI/visionq. Data: https://huggingface.co/datasets/visionq-anon-2026/VisionQ-1k.

  • 9 authors
·
Sep 29

CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling

Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while frontier-language-model judges are too expensive to call at every step and cannot be assumed available at deployment. We introduce CLIFT, a training and test-time scaling method built around conformal self-verification. During training, the agent answers natural-language verification questions about its own rollouts; a Compositional Conformal Certifier keeps only question signals whose URL-conditional evidence agrees with a training-time judge, assigns signed trust weights through polarity-aware lift, and blends the resulting verifier score into per-step rewards in a way that never subtracts from the judge baseline. At test time, the same certified bank is frozen and reused as structured evidence for Conformal Trajectory Selection (CTS): the agent samples a greedy rollout and one or more diverse retries, the self-verifier summarises each URL trace, and a conservative majority-vote rule chooses whether to swap away from the current incumbent without calling any external judge. This single mechanism supports three settings. On WebArena Infinity, CLIFT achieves state-of-the-art performance among open-source web agents. On VisualWebArena, a bank trained with the open model transfers to GPT-5.5 at test time and reaches state-of-the-art performance under the canonical harness. On Online Mind2Web, without training an agent on the benchmark, translating the certified question bank improves a live-web agent in zero-shot evaluation. Together these results position conformal self-verification as a way to turn costly judge feedback into a reusable training signal and a judge-free test-time scaling signal.

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates

LLM-as-a-Judge has been widely applied to evaluate and compare different LLM alignmnet approaches (e.g., RLHF and DPO). However, concerns regarding its reliability have emerged, due to LLM judges' biases and inconsistent decision-making. Previous research has developed evaluation frameworks to assess reliability of LLM judges and their alignment with human preferences. However, the employed evaluation metrics often lack adequate explainability and fail to address LLM internal inconsistency. Additionally, existing studies inadequately explore the impact of various prompt templates when applying LLM-as-a-Judge methods, leading to potentially inconsistent comparisons between different alignment algorithms. In this work, we systematically evaluate LLM-as-a-Judge on alignment tasks by defining more theoretically interpretable evaluation metrics and explicitly mitigating LLM internal inconsistency from reliability metrics. We develop an open-source framework to evaluate, compare, and visualize the reliability and alignment of LLM judges, which facilitates practitioners to choose LLM judges for alignment tasks. In the experiments, we examine effects of diverse prompt templates on LLM-judge reliability and also demonstrate our developed framework by comparing various LLM judges on two common alignment datasets (i.e., TL;DR Summarization and HH-RLHF-Helpfulness). Our results indicate a significant impact of prompt templates on LLM judge performance, as well as a mediocre alignment level between the tested LLM judges and human evaluators.

  • 7 authors
·
Aug 23, 2024

ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation

Recent advances in instruction-guided image editing underscore the need for effective automated evaluation. While Vision-Language Models (VLMs) have been explored as judges, open-source models struggle with alignment, and proprietary models lack transparency and cost efficiency. Additionally, no public training datasets exist to fine-tune open-source VLMs, only small benchmarks with diverse evaluation schemes. To address this, we introduce ADIEE, an automated dataset creation approach which is then used to train a scoring model for instruction-guided image editing evaluation. We generate a large-scale dataset with over 100K samples and use it to fine-tune a LLaVA-NeXT-8B model modified to decode a numeric score from a custom token. The resulting scorer outperforms all open-source VLMs and Gemini-Pro 1.5 across all benchmarks, achieving a 0.0696 (+17.24%) gain in score correlation with human ratings on AURORA-Bench, and improving pair-wise comparison accuracy by 4.03% (+7.21%) on GenAI-Bench and 4.75% (+9.35%) on AURORA-Bench, respectively, compared to the state-of-the-art. The scorer can act as a reward model, enabling automated best edit selection and model fine-tuning. Notably, the proposed scorer can boost MagicBrush model's average evaluation score on ImagenHub from 5.90 to 6.43 (+8.98%). Our code and models are available at https://github.com/SherryXTChen/ADIEE.git.

  • 4 authors
·
Jul 9, 2025

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

While text-to-image models like DALLE-3 and Stable Diffusion are rapidly proliferating, they often encounter challenges such as hallucination, bias, and the production of unsafe, low-quality output. To effectively address these issues, it is crucial to align these models with desired behaviors based on feedback from a multimodal judge. Despite their significance, current multimodal judges frequently undergo inadequate evaluation of their capabilities and limitations, potentially leading to misalignment and unsafe fine-tuning outcomes. To address this issue, we introduce MJ-Bench, a novel benchmark which incorporates a comprehensive preference dataset to evaluate multimodal judges in providing feedback for image generation models across four key perspectives: alignment, safety, image quality, and bias. Specifically, we evaluate a large variety of multimodal judges including smaller-sized CLIP-based scoring models, open-source VLMs (e.g. LLaVA family), and close-source VLMs (e.g. GPT-4o, Claude 3) on each decomposed subcategory of our preference dataset. Experiments reveal that close-source VLMs generally provide better feedback, with GPT-4o outperforming other judges in average. Compared with open-source VLMs, smaller-sized scoring models can provide better feedback regarding text-image alignment and image quality, while VLMs provide more accurate feedback regarding safety and generation bias due to their stronger reasoning capabilities. Further studies in feedback scale reveal that VLM judges can generally provide more accurate and stable feedback in natural language (Likert-scale) than numerical scales. Notably, human evaluations on end-to-end fine-tuned models using separate feedback from these multimodal judges provide similar conclusions, further confirming the effectiveness of MJ-Bench. All data, code, models are available at https://huggingface.co/MJ-Bench.

  • 19 authors
·
Jul 5, 2024 5

CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges

Evaluating the occurrence and triggers of large language model (LLM) behaviors - such as sycophancy, self-preference, or over-confidence - is critical for predicting real-world model deployment risks. However, existing situated behavioral evaluations typically ignore cultural context, limiting their generalizability across an increasingly global user base. To address this gap, we propose CuBEs - Culturally-situated Behavior Evaluations that probe for response patterns across diverse user cultures. We first extend an automated testing pipeline to inject cultural context into behavioral test scenarios and subsequent evaluation. We assess the cultural adaptability of this pipeline by building a human-labeled dataset that captures nuanced dimensions of behavior understanding across 12 distinct cultures. Our dataset reveals significant cross-cultural variations that one-size-fits all judgments fail to capture. Through evaluating 13 open- and closed-source LLMs, we find that introducing cultural situatedness in the evaluation scenario creates significant variation in the presence of a behavior. For example, while our baseline experiments testing for political bias capture localized Western political dimensions like the American conservative-progressive divide, non-Western culturally situated evaluations surface entirely different axes of bias such as religious and colonial political issues. Our findings demonstrate that standard, culturally-agnostic evaluations fail to capture these shifts, highlighting the necessity of culturally situated behavioral testing for global deployments.

  • 3 authors
·
Oct 1

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls

Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipelines where data generation and model training are executed as two separate, non-interactive processes. This approach fails to adaptively focus on a model's specific weaknesses and allows noisy labels to persist, degrading training efficiency. We introduce LoopTool, a fully automated, model-aware data evolution framework that closes this loop by tightly integrating data synthesis and model training. LoopTool iteratively refines both the data and the model through three synergistic modules: (1) Greedy Capability Probing (GCP) diagnoses the model's mastered and failed capabilities; (2) Judgement-Guided Label Verification (JGLV) uses an open-source judge model to find and correct annotation errors, progressively purifying the dataset; and (3) Error-Driven Data Expansion (EDDE) generates new, challenging samples based on identified failures. This closed-loop process operates within a cost-effective, open-source ecosystem, eliminating dependence on expensive closed-source APIs. Experiments show that our 8B model trained with LoopTool significantly surpasses its 32B data generator and achieves new state-of-the-art results on the BFCL-v3 and ACEBench benchmarks for its scale. Our work demonstrates that closed-loop, self-refining data pipelines can dramatically enhance the tool-use capabilities of LLMs.

Self-Judge: Selective Instruction Following with Alignment Self-Evaluation

Pre-trained large language models (LLMs) can be tailored to adhere to human instructions through instruction tuning. However, due to shifts in the distribution of test-time data, they may not always execute instructions accurately, potentially generating factual errors or misaligned content when acting as chat assistants. To enhance the reliability of LLMs in following instructions, we propose the study of selective instruction following, whereby the system declines to execute instructions if the anticipated response quality is low. We train judge models that can predict numerical quality scores for model responses. To address data scarcity, we introduce Self-J, a novel self-training framework for developing judge models without needing human-annotated quality scores. Our method leverages the model's inherent self-evaluation capability to extract information about response quality from labeled instruction-tuning data. It incorporates a gold reference answer to facilitate self-evaluation and recalibrates by assessing the semantic similarity between the response sample and the gold reference. During the training phase, we implement self-distillation as a regularization technique to enhance the capability of reference-free estimation. To validate alignment evaluation on general instruction-following tasks, we collect large-scale high-quality instructions from Hugging Face for model training and evaluation. Extensive experiments on five open-source models show that our method correlates much more with GPT-4 than strong baselines, e.g., supervised models distilled from GPT-4 and GPT-3.5-turbo. Our analysis shows our model's strong generalization across domains. Additionally, our judge models serve as good reward models, e.g., boosting WizardLM-13B-V1.2 from 89.17 to 92.48 and from 12.03 to 15.90 in version v1 and v2 of AlpacaEval respectively using best-of-32 sampling with our judge models.

  • 2 authors
·
Sep 2, 2024

CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution

Efficient and accurate evaluation is crucial for the continuous improvement of large language models (LLMs). Among various assessment methods, subjective evaluation has garnered significant attention due to its superior alignment with real-world usage scenarios and human preferences. However, human-based evaluations are costly and lack reproducibility, making precise automated evaluators (judgers) vital in this process. In this report, we introduce CompassJudger-1, the first open-source all-in-one judge LLM. CompassJudger-1 is a general-purpose LLM that demonstrates remarkable versatility. It is capable of: 1. Performing unitary scoring and two-model comparisons as a reward model; 2. Conducting evaluations according to specified formats; 3. Generating critiques; 4. Executing diverse tasks like a general LLM. To assess the evaluation capabilities of different judge models under a unified setting, we have also established JudgerBench, a new benchmark that encompasses various subjective evaluation tasks and covers a wide range of topics. CompassJudger-1 offers a comprehensive solution for various evaluation tasks while maintaining the flexibility to adapt to diverse requirements. Both CompassJudger and JudgerBench are released and available to the research community athttps://github.com/open-compass/CompassJudger. We believe that by open-sourcing these tools, we can foster collaboration and accelerate progress in LLM evaluation methodologies.

  • 6 authors
·
Oct 21, 2024 2

Improve LLM-as-a-Judge Ability as a General Ability

LLM-as-a-Judge leverages the generative and reasoning capabilities of large language models (LLMs) to evaluate LLM responses across diverse scenarios, providing accurate preference signals. This approach plays a vital role in aligning LLMs with human values, ensuring ethical and reliable AI outputs that align with societal norms. Recent studies have raised many methods to train LLM as generative judges, but most of them are data consuming or lack accuracy, and only focus on LLM's judge ability. In this work, we regard judge ability as a general ability of LLM and implement a two-stage training approach, comprising supervised fine-tuning (SFT) warm-up and direct preference optimization (DPO) enhancement, to achieve judge style adaptation and improve judgment accuracy. Additionally, we introduce an efficient data synthesis method to generate judgmental content. Experimental results demonstrate that our approach, utilizing only about 2% to 40% of the data required by other methods, achieves SOTA performance on RewardBench. Furthermore, our training method enhances the general capabilities of the model by constructing complicated judge task, and the judge signals provided by our model have significantly enhanced the downstream DPO training performance of our internal models in our test to optimize policy model with Judge Model. We also open-source our model weights and training data to facilitate further research.

  • 6 authors
·
Feb 17, 2025

Judge's Verdict: A Comprehensive Analysis of LLM Judge Capability Through Human Agreement

This research introduces the Judge's Verdict Benchmark, a novel two-step methodology to evaluate Large Language Models (LLMs) as judges for response accuracy evaluation tasks. We assess how well 54 LLMs can replicate human judgment when scoring responses from RAG (Retrieval-Augmented Generation) or Agentic pipelines against ground truth answers. Our methodology progresses from traditional correlation analysis to comprehensive Cohen's Kappa analysis that measures actual agreement patterns. The two-step approach includes: (1) a correlation test that filters judges with strong alignment, followed by (2) a human-likeness test using z-scores to identify two distinct judgment patterns: human-like judgment (|z| < 1) that mimics natural human variation, and super-consistent judgment (z > 1) that exceeds typical human-to-human agreement levels. This methodology reveals that 27 out of 54 tested LLMs achieve Tier 1 performance: 23 models exhibit human-like patterns that preserve the nuances of human judgment, while 4 models demonstrate super-consistent behavior, a pattern that could indicate either enhanced reliability or oversimplification of complex judgments. Testing 43 open-source models (1B-405B parameters) and 11 closed models (GPT, Gemini, Claude variants), we demonstrate that judge excellence is not solely dependent on model size but on specific training strategies. Our key contributions include: (1) establishing that correlation alone is insufficient for judge evaluation, (2) introducing a "Turing Test for judges" based on agreement patterns, and (3) providing a standardized benchmark for classifying LLM judges into distinct performance tiers for different evaluation needs.

  • 4 authors
·
Oct 9, 2025

EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge

Text-to-Speech (TTS) benchmarks often fail to capture how well models handle nuanced and semantically complex text. Building on EmergentTTS, we introduce EmergentTTS-Eval, a comprehensive benchmark covering six challenging TTS scenarios: emotions, paralinguistics, foreign words, syntactic complexity, complex pronunciation (e.g. URLs, formulas), and questions. Crucially, our framework automates both test-case generation and evaluation, making the benchmark easily extensible. Starting from a small set of human-written seed prompts, we iteratively extend them using LLMs to target specific structural, phonetic and prosodic challenges, resulting in 1,645 diverse test cases. Moreover, we employ a model-as-a-judge approach, using a Large Audio Language Model (LALM) to assess the speech across multiple dimensions such as expressed emotion, prosodic, intonational, and pronunciation accuracy. We evaluate state-of-the-art open-source and proprietary TTS systems, such as 11Labs, Deepgram, and OpenAI's 4o-mini-TTS, on EmergentTTS-Eval, demonstrating its ability to reveal fine-grained performance differences. Results show that the model-as-a-judge approach offers robust TTS assessment and a high correlation with human preferences. We open source the evaluation https://github.com/boson-ai/EmergentTTS-Eval-public{code} and the https://huggingface.co/datasets/bosonai/EmergentTTS-Eval{dataset}.

  • 5 authors
·
May 28, 2025 2

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks

Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text. This paradigm offers scalability and cost-effectiveness compared to human annotation. However, the reliability and security of such systems, particularly their robustness against adversarial manipulations, remain critical concerns. This paper investigates the vulnerability of LLM-as-a-Judge architectures to prompt-injection attacks, where malicious inputs are designed to compromise the judge's decision-making process. We formalize two primary attack strategies: Comparative Undermining Attack (CUA), which directly targets the final decision output, and Justification Manipulation Attack (JMA), which aims to alter the model's generated reasoning. Using the Greedy Coordinate Gradient (GCG) optimization method, we craft adversarial suffixes appended to one of the responses being compared. Experiments conducted on the MT-Bench Human Judgments dataset with open-source instruction-tuned LLMs (Qwen2.5-3B-Instruct and Falcon3-3B-Instruct) demonstrate significant susceptibility. The CUA achieves an Attack Success Rate (ASR) exceeding 30\%, while JMA also shows notable effectiveness. These findings highlight substantial vulnerabilities in current LLM-as-a-Judge systems, underscoring the need for robust defense mechanisms and further research into adversarial evaluation and trustworthiness in LLM-based assessment frameworks.

  • 3 authors
·
May 18, 2025

Generative Judge for Evaluating Alignment

The rapid development of Large Language Models (LLMs) has substantially expanded the range of tasks they can address. In the field of Natural Language Processing (NLP), researchers have shifted their focus from conventional NLP tasks (e.g., sequence tagging and parsing) towards tasks that revolve around aligning with human needs (e.g., brainstorming and email writing). This shift in task distribution imposes new requirements on evaluating these aligned models regarding generality (i.e., assessing performance across diverse scenarios), flexibility (i.e., examining under different protocols), and interpretability (i.e., scrutinizing models with explanations). In this paper, we propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios and accommodates diverse evaluation protocols (e.g., pairwise response comparison and single-response evaluation) with well-structured natural language critiques. To demonstrate the efficacy of our approach, we construct a new testbed covering 58 different scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models, by a large margin. We also provide detailed analysis and case studies to further reveal the potential of our method and make a variety of resources public at https://github.com/GAIR-NLP/auto-j.

  • 6 authors
·
Oct 9, 2023

VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation

Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perceptual dimensions separately and fail to capture the overall semantic and temporal coherence among the text prompt, video, and audio that shapes human preferences. Optimizing models against these metrics encourages reward hacking, generating video-audio content that achieves high scores on these metrics yet appears incoherent or unfaithful to human viewers. To address this problem, we first construct a large-scale human-preference dataset VAPref-10K for joint video-audio generation, comprising 9K prompts and 10.3K fine-grained paired comparisons from open-source generation models. We also introduce the VA-Judger-Bench benchmark with both in-domain and out-of-domain model comparisons to evaluate whether reward models truly align with human preferences. We further propose VA-Judger, a chain-of-thought omni-reward model for joint video-audio generation. In particular, VA-Judger first learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, and finally performs dimension-wise reinforcement learning that decomposes human feedback into individual quality dimensions for denser reward signals than a single binary preference label. Experiments show that VA-Judger outperforms metric baselines in predicting human preferences on both in-domain and out-of-domain evaluations. Using its human-aligned rewards for post-training audio-video generation model also yields significant improvements in generation quality.

Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations

LLM-as-judge ("grader") components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream deployment decisions. A widespread assumption is that setting the grader's sampling temperature to 0 makes grading deterministic. We test this assumption against a real safety-evaluation codebase (Japan AISI's open-source aisev) and show it fails on two levels. First, the harness invokes its grader without setting temperature or seed; the underlying provider silently applies its default of 1.0, so items near the decision boundary flip pass/fail across identical runs (per-item disagreement up to ~50% over 20 runs). Second, pinning temperature=0 reduces but does not eliminate flips: across 690 API calls spanning two providers, three model tiers, and five sampling configurations, 1-2 of 7 borderline items remain non-reproducible even under forced greedy decoding (top_k=1). Claude Opus 4.7/4.8 has since deprecated temperature entirely, rendering the primary mitigation inapplicable to newer model generations. These findings expose a structural gap: evaluation harnesses that report single-run verdicts without variance or grader-disagreement metrics can present noise as a safety property. We release a reproduction harness (690 calls, 7 conditions) and recommend that harnesses treat grader disagreement as a first-class health metric alongside the scores themselves.

  • 1 authors
·
Jun 23

PentestJudge: Judging Agent Behavior Against Operational Requirements

We introduce PentestJudge, a system for evaluating the operations of penetration testing agents. PentestJudge is a large language model (LLM)-as-judge with access to tools that allow it to consume arbitrary trajectories of agent states and tool call history to determine whether a security agent's actions meet certain operating criteria that would be impractical to evaluate programmatically. We develop rubrics that use a tree structure to hierarchically collapse the penetration testing task for a particular environment into smaller, simpler, and more manageable sub-tasks and criteria until each leaf node represents simple yes-or-no criteria for PentestJudge to evaluate. Task nodes are broken down into different categories related to operational objectives, operational security, and tradecraft. LLM-as-judge scores are compared to human domain experts as a ground-truth reference, allowing us to compare their relative performance with standard binary classification metrics, such as F1 scores. We evaluate several frontier and open-source models acting as judge agents, with the best model reaching an F1 score of 0.83. We find models that are better at tool-use perform more closely to human experts. By stratifying the F1 scores by requirement type, we find even models with similar overall scores struggle with different types of questions, suggesting certain models may be better judges of particular operating criteria. We find that weaker and cheaper models can judge the trajectories of pentests performed by stronger and more expensive models, suggesting verification may be easier than generation for the penetration testing task. We share this methodology to facilitate future research in understanding the ability of judges to holistically and scalably evaluate the process quality of AI-based information security agents so that they may be confidently used in sensitive production environments.

  • 5 authors
·
Aug 4, 2025

PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology

Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safety. As patients and clinicians increasingly use LLMs for guidance on complex conditions such as pancreatic cancer, evaluation must extend beyond general medical knowledge. Existing frameworks, such as HealthBench, rely on simulated queries and lack disease-specific depth. Moreover, high rubric-based scores do not ensure factual correctness, underscoring the need to assess hallucinations. We developed a human-in-the-loop pipeline to create expert rubrics for de-identified patient questions from the Pancreatic Cancer Action Network (PanCAN). The resulting benchmark, PanCanBench, includes 3,130 question-specific criteria across 282 authentic patient questions. We evaluated 22 proprietary and open-source LLMs using an LLM-as-a-judge framework, measuring clinical completeness, factual accuracy, and web-search integration. Models showed substantial variation in rubric-based completeness, with scores ranging from 46.5% to 82.3%. Factual errors were common, with hallucination rates (the percentages of responses containing at least one factual error) ranging from 6.0% for Gemini-2.5 Pro and GPT-4o to 53.8% for Llama-3.1-8B. Importantly, newer reasoning-optimized models did not consistently improve factuality: although o3 achieved the highest rubric score, it produced inaccuracies more frequently than other GPT-family models. Web-search integration did not inherently guarantee better responses. The average score changed from 66.8% to 63.9% for Gemini-2.5 Pro and from 73.8% to 72.8% for GPT-5 when web search was enabled. Synthetic AI-generated rubrics inflated absolute scores by 17.9 points on average while generally maintaining similar relative ranking.

  • 16 authors
·
Mar 1

DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent

Deep-research agents are capable of executing multi-step web exploration, targeted retrieval, and sophisticated question answering. Despite their powerful capabilities, deep-research agents face two critical bottlenecks: (1) the lack of large-scale, challenging datasets with real-world difficulty, and (2) the absence of accessible, open-source frameworks for data synthesis and agent training. To bridge these gaps, we first construct DeepResearch-9K, a large-scale challenging dataset specifically designed for deep-research scenarios built from open-source multi-hop question-answering (QA) datasets via a low-cost autonomous pipeline. Notably, it consists of (1) 9000 questions spanning three difficulty levels from L1 to L3 (2) high-quality search trajectories with reasoning chains from Tongyi-DeepResearch-30B-A3B, a state-of-the-art deep-research agent, and (3) verifiable answers. Furthermore, we develop an open-source training framework DeepResearch-R1 that supports (1) multi-turn web interactions, (2) different reinforcement learning (RL) approaches, and (3) different reward models such as rule-based outcome reward and LLM-as-judge feedback. Finally, empirical results demonstrate that agents trained on DeepResearch-9K under our DeepResearch-R1 achieve state-of-the-art results on challenging deep-research benchmarks. We release the DeepResearch-9K dataset on https://huggingface.co/datasets/artillerywu/DeepResearch-9K and the code of DeepResearch-R1 on https://github.com/Applied-Machine-Learning-Lab/DeepResearch-R1.

  • 7 authors
·
Mar 1

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

Scalable Vector Graphics (SVG) are an essential format for technical illustration and digital design, offering precise resolution independence and flexible semantic editability. In practice, however, original vector source files are frequently lost or inaccessible, leaving only "flat" rasterized versions (e.g., PNG or JPEG) that are difficult to modify or scale. Manually reconstructing these figures is a prohibitively labor-intensive process, requiring specialized expertise to recover the original geometric intent. To bridge this gap, we propose VFIG, a family of Vision-Language Models trained for complex and high-fidelity figure-to-SVG conversion. While this task is inherently data-driven, existing datasets are typically small-scale and lack the complexity of professional diagrams. We address this by introducing VFIG-DATA, a large-scale dataset of 66K high-quality figure-SVG pairs, curated from a diverse mix of real-world paper figures and procedurally generated diagrams. Recognizing that SVGs are composed of recurring primitives and hierarchical local structures, we introduce a coarse-to-fine training curriculum that begins with supervised fine-tuning (SFT) to learn atomic primitives and transitions to reinforcement learning (RL) refinement to optimize global diagram fidelity, layout consistency, and topological edge cases. Finally, we introduce VFIG-BENCH, a comprehensive evaluation suite with novel metrics designed to measure the structural integrity of complex figures. VFIG achieves state-of-the-art performance among open-source models and performs on par with GPT-5.2, achieving a VLM-Judge score of 0.829 on VFIG-BENCH.

MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Safety evaluation and red-teaming of large language models remain predominantly text-centric, and existing frameworks lack the infrastructure to systematically test whether alignment generalizes to audio, image, and video inputs. We present MUSE (Multimodal Unified Safety Evaluation), an open-source, run-centric platform that integrates automatic cross-modal payload generation, three multi-turn attack algorithms (Crescendo, PAIR, Violent Durian), provider-agnostic model routing, and an LLM judge with a five-level safety taxonomy into a single browser-based system. A dual-metric framework distinguishes hard Attack Success Rate (Compliance only) from soft ASR (including Partial Compliance), capturing partial information leakage that binary metrics miss. To probe whether alignment generalizes across modality boundaries, we introduce Inter-Turn Modality Switching (ITMS), which augments multi-turn attacks with per-turn modality rotation. Experiments across six multimodal LLMs from four providers show that multi-turn strategies can achieve up to 90-100% ASR against models with near-perfect single-turn refusal. ITMS does not uniformly raise final ASR on already-saturated baselines, but accelerates convergence by destabilizing early-turn defenses, and ablation reveals that the direction of modality effects is model-family-specific rather than universal, underscoring the need for provider-aware cross-modal safety testing.

  • 5 authors
·
Mar 2 2

PhyGround: Benchmarking Physical Reasoning in Generative World Models

Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these rules remains challenging. Existing physics-focused video benchmarks have made important progress, but they still face three key challenges, including the coarse evaluation frameworks that hide law-specific failures, response biases and fatigue that undermine the validity of annotation judgments, and automated evaluators that are insufficiently physics-aware or difficult to audit. To address those challenges, we introduce PhyGround, a criteria-grounded benchmark for evaluating physical reasoning in video generation. The benchmark contains 250 curated prompts, each augmented with an expected physical outcome, and a taxonomy of 13 physical laws across solid-body mechanics, fluid dynamics, and optics. Each law is operationalized through observable sub-questions to enable per-law diagnostics. We evaluate eight modern video generation models through a large-scale, quality-controlled human study, grounded on social science lab experiment design. A total of 459 annotators provided 5,796 complete annotations and over 37.4K fine-grained labels; after quality control, the retained annotations exhibited high split-half model-ranking correlations (Spearman's rho > 0.90). To support reproducible automated evaluation, we release PhyJudge-9B, an open physics-specialized VLM judge. PhyJudge-9B achieves substantially lower aggregate relative bias than Gemini-3.1-Pro (3.3% vs. 16.6%). We release prompts, human annotations, model checkpoints, and evaluation code on the project page https://phyground.github.io/.

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications

Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories (aiohttp, aiogram, Laravel, NestJS, Fastify), each specified natively in Russian -- written from scratch, not translated -- and judged by the upstream maintainer's regression tests, which we withhold from release. All fix commits postdate the training-data cutoffs of every evaluated model. Round 1 evaluates Claude Code with Opus 4.8, Sonnet 5, and Haiku 4.5, and Codex CLI with GPT-5.5 (3 independent runs each; pass@1 with task-level uncertainty); the best configuration resolves 78.7% of tasks. Auditing full trajectories of an hors-concours configuration (Claude Code + Fable 5), we caught the product silently substituting the model on 20% of tasks via an official safeguard fallback -- evidence that the deployed product, not the model, is the unit actually measured. Version 2 adds Round 2: seven further configurations on the same frozen set under a per-configuration freshness gate -- the Russian-market agents SourceCraft CLI (ds, legacy) and Koda CLI (koda-pro), Antigravity with Gemini 3.1 Pro and 3.5 Flash, and Codex CLI with GPT-5.6 Sol and Luna. SourceCraft's flagship resolves 68.1% (N=23), above GPT-5.5 and both Gemini rows. A tool-call contamination re-audit of all 437 Round-2 trajectories finds the Russian and Gemini columns clean (0/293 cells) while flagging systematic oracle-hunting in the GPT-5.6 family (8/69 and 13/75 cells), including one case of mining a prior round's artifacts from the run machine's disk; honest scores are published alongside raw ones. We release statements, metadata, trajectories, and diffs; oracles are withheld with a SHA-256 manifest.

  • 1 authors
·
Jul 18

Enabling Weak LLMs to Judge Response Reliability via Meta Ranking

Despite the strong performance of large language models (LLMs) across a wide range of tasks, they still have reliability issues. Previous studies indicate that strong LLMs like GPT-4-turbo excel in evaluating the reliability of responses from LLMs, but face efficiency and local deployment issues. Thus, to enable weak LLMs to effectively assess the reliability of LLM responses, we propose a novel cross-query-comparison-based method called Meta Ranking (MR). Unlike previous few-shot methods that solely based on in-context learning capabilities in LLMs, MR assesses reliability by pairwisely ranking the target query-response pair with multiple reference query-response pairs. We found that MR is highly effective in error detection for LLM responses, where weak LLMs, such as Phi-2, could surpass strong baselines like GPT-3.5-turbo, requiring only five reference samples and significantly improving efficiency. We further demonstrate that MR can enhance strong LLMs' performance in two practical applications: model cascading and instruction tuning. In model cascading, we combine open- and closed-source LLMs to achieve performance comparable to GPT-4-turbo with lower costs. In instruction tuning, we use MR for iterative training data filtering, significantly reducing data processing time and enabling LLaMA-7B and Phi-2 to surpass Alpaca-13B with fewer training tokens. These results underscore the high potential of MR in both efficiency and effectiveness.

  • 7 authors
·
Feb 19, 2024

RoboJev: An Open Vision-Language Judge for Robot Success Detection

Many robot manipulation videos do not indicate whether the task was successfully completed. RoboJev-27B is an open-weight vision-language model that takes a task instruction, 10 frames of a manipulation attempt, and (if available) final frames from auxiliary cameras and predicts whether the robot accomplished the task. RoboJev-27B is a variant of JEV-27B-VL, trained with a rank-32 LoRA adapter on the language model only (keeping the vision encoder frozen) using 52,598 episode records. It also uses a source-specific KL penalty that applies only to research data, anchoring predictions closer to the original model on those sources. It uses a calibrated two-token readout that outputs success/failure probabilities in a single forward pass. On 268 held-out episodes of the same robot model (SO-101), RoboJev-27B attains 95.2% balanced accuracy and 0.993 AUROC. It also generalises to episodes collected by unseen labs/robots (AUROC = 0.890 over 459 episodes) as well as to clearly labelled community-collected episodes (accuracy = 93.3% over 135 episodes), where the base model attains an AUROC = 0.900 on the unseen-lab/robot subset with the same inputs. It takes 0.26 seconds per episode (median, serial) to infer on a single H100, which is about \0.19 per 1,000 success predictions at 2.69 per GPU-hour (not including media processing and serving costs). RoboJev-27B is released together with its inference code, along with a transparent evaluation: 20,628 predictions organized into 29 model/protocol entries are made available to facilitate browsing and to enable reproducible benchmarking of success detection. We also compare against strong API-based frontier VLMs, which take in fewer input frames (4 images from the primary camera only); note that this comparison is not strictly like-for-like because RoboJev-27B is given more frames at inference.

  • 1 authors
·
Oct 23 2

Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks

Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals for reinforcement fine-tuning (RFT). However, rubric generation remains hard to control: rubrics often lack coverage, conflate dimensions, misalign preference direction, and contain redundant or highly correlated criteria, degrading judge accuracy and producing suboptimal rewards during RFT. We propose RRD, a principled framework for rubric refinement built on a recursive decompose-filter cycle. RRD decomposes coarse rubrics into fine-grained, discriminative criteria, expanding coverage while sharpening separation between responses. A complementary filtering mechanism removes misaligned and redundant rubrics, and a correlation-aware weighting scheme prevents over-representing highly correlated criteria, yielding rubric sets that are informative, comprehensive, and non-redundant. Empirically, RRD delivers large, consistent gains across both evaluation and training: it improves preference-judgment accuracy on JudgeBench and PPE for both GPT-4o and Llama3.1-405B judges, achieving top performance in all settings with up to +17.7 points on JudgeBench. When used as the reward source for RFT on WildChat, it yields substantially stronger and more stable learning signals, boosting reward by up to 160% (Qwen3-4B) and 60% (Llama3.1-8B) versus 10-20% for prior rubric baselines, with gains that transfer to HealthBench-Hard and BiGGen Bench. Overall, RRD establishes recursive rubric refinement as a scalable and interpretable foundation for LLM judging and reward modeling in open-ended domains.

  • 9 authors
·
Feb 4

CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding

Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their implicit engineering knowledge ---i.e., the algorithms they implement, the paradigms they follow, the patterns they instantiate, and the application domains they serve--- remains challenging, as current tools are constrained to syntactic and token-level analysis. We present a pipeline for building an open-taxonomy semantic annotation of source code using a code-specialised Large Language Model. The extracted entities are grounded in Wikidata through a three-stage linking procedure: a deterministic SPARQL stage handles unambiguous entities, a Deep Research Agent resolves the residual long tail, and a hierarchy-rollup stage imports the parent-of closure of each resolved Wikidata identifier. The resulting annotations are materialised as a source-code-specific open-taxonomy knowledge graph. We further introduce a calibrated quality-assurance protocol that quantifies annotation precision by combining a small human gold set with an LLM-as-a-judge filter. We applied our pipeline to the 167 million files of the Stack-Edu corpus, creating the first known large-scale open-taxonomy knowledge graph for source code. Our graph, named CodeGraph, contains approximately 158 million nodes, which include around 145 million files, about 63,000 extracted concept entities (such as algorithms, paradigms, design patterns, and application domains), and roughly 19,800 grounded Wikidata entities. Furthermore, CodeGraph features approximately 1 billion typed edges that connect files to their respective concepts, link these concepts to their grounded Wikidata identifiers, and relate them to their parent categories, covering 14 programming languages.

  • 5 authors
·
Sep 23 2

JudgeBench: A Benchmark for Evaluating LLM-based Judges

LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized. As LLMs become more advanced, their responses grow more sophisticated, requiring stronger judges to evaluate them. Existing benchmarks primarily focus on a judge's alignment with human preferences, but often fail to account for more challenging tasks where crowdsourced human preference is a poor indicator of factual and logical correctness. To address this, we propose a novel evaluation framework to objectively evaluate LLM-based judges. Based on this framework, we propose JudgeBench, a benchmark for evaluating LLM-based judges on challenging response pairs spanning knowledge, reasoning, math, and coding. JudgeBench leverages a novel pipeline for converting existing difficult datasets into challenging response pairs with preference labels reflecting objective correctness. Our comprehensive evaluation on a collection of prompted judges, fine-tuned judges, multi-agent judges, and reward models shows that JudgeBench poses a significantly greater challenge than previous benchmarks, with many strong models (e.g., GPT-4o) performing just slightly better than random guessing. Overall, JudgeBench offers a reliable platform for assessing increasingly advanced LLM-based judges. Data and code are available at https://github.com/ScalerLab/JudgeBench .

  • 8 authors
·
Oct 16, 2024 2

WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality

The paradigm of LLM-as-a-judge is emerging as a scalable and efficient alternative to human evaluation, demonstrating strong performance on well-defined tasks. However, its reliability in open-ended tasks with dynamic environments and complex interactions remains unexplored. To bridge the gap, we introduce WebDevJudge, a systematic benchmark for assessing LLM-as-a-judge performance in web development, with support for both non-interactive evaluation based on static observations and continuous interactive evaluation with a dynamic web environment. WebDevJudge comprises human preference labels over paired web implementations, annotated with structured and query-grounded rubrics to ensure high-quality ground truth. Using this benchmark, we comprehensively evaluate various evaluators, including LLMs, MLLMs, and agentic workflows. We systematically investigate the impact of different paradigms and guidance mechanisms. Our experiments reveal a significant gap between LLM judges and human experts. In-depth analysis indicates this gap stems from fundamental model limitations, including failures in recognizing functional equivalence, verifying task feasibility, and mitigating bias. Overall, WebDevJudge presents a significant challenge to LLM-as-a-judge, offering insights to guide future research toward developing more reliable and capable automated evaluators for complicated scenarios. Code and data are available at https://github.com/lcy2723/WebDevJudge.

  • 8 authors
·
Oct 21, 2025

AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling

LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined. We present AgentJudgeBench, the first benchmark to systematically study LLM-as-a-judge reliability for agentic tool-calling over workflow DAGs, as distinct from the broader LLM-as-a-judge task of open-ended text or preference evaluation. The benchmark comprises 3,808 instances spanning six DAG topologies and three difficulty tiers, evaluated with five generators (3B-70B open-weight models and GPT-5.4) and six judges (20B to frontier scale) under paired with- and without-ground-truth conditions. Judge alignment degrades monotonically with task difficulty, 1.5x faster without ground truth, and on hard queries without ground truth all six judges converge to a narrow 77-82% band regardless of scale, revealing a structural ceiling driven primarily by task difficulty, though its height is partly prompt-dependent for weaker generators, that model capacity alone cannot overcome. Ground-truth exposure is not uniformly beneficial: it reduces alignment for GPT-5.4 (1.5 pp) and Gemini-2.5-Pro (3.9 pp), consistent with over-anchoring. Among mitigation strategies, chain-of-thought reasoning and judge temperature both have negligible effect, while structured evaluation rubrics improve alignment by up to 6.5 pp but do not generalize uniformly across judge-generator pairs. With ground truth, QwQ-32B best matches the programmatic reference, while a human validation study identifies GPT-OSS-120B as the most human-aligned judge; without it, frontier judges lead only marginally within the shared ceiling. These results expose fundamental limitations of current LLM judges and yield practical guidelines for reliable evaluation in agentic systems.

ServiceNow-AI ServiceNow-AI
·
Aug 26 2

WorldBench: Evaluating LLMs on Three.js Voxel World Generation

Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges take one view of the output: a vision-language model scores a few rendered snapshots, or a language model reads the source. On worlds written by five frontier models we find that the two views disagree on 32% of required items, mostly code that no frame shows, and that fixed views miss small close-up contents. We present WorldBench, a benchmark and judge for open-ended, LLM-generated Three.js worlds. From one prompt describing a floating voxel island with ten biomes, physics, and day/night and seasonal cycles, the judge explores the running world, controlling its clock, orbiting it, and sending a navigator agent to frame each biome, and reads the code for what it sees. Neither channel is trusted on its own: a code quote counts only if it is text the source contains, and visual claims are checked against measured pixels where the property is measurable. A mutation test, in which we remove features by construction, shows that code-only judging gives full credit to four of five removed features, because their code remains in the file. Our judge cuts the points kept on removed features by a third (5.44 to 3.55 of 7.11), and what it still credits is mostly code that exists but never runs. We evaluate five frontier models: Claude Fable 5.1, GPT-6 Astra, Kimi K3, Grok 4.7 and Gemini 3.1 Pro. Code, prompt, tests and judge configuration are available at https://github.com/KrishBakshi/worldbench

  • 1 authors
·
Oct 6 1

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

As agentic systems tackle increasingly complex multi-step tasks, evaluating their trajectories presents a major bottleneck - human annotation of a single trajectory on popular agentic benchmarks can take hours, making it difficult to scale evaluations for measuring performance or curating training data. This has driven widespread reliance on automated approaches such as LLM-as-a-judge (LLMJ) to critique agents at the process and outcome-levels at scale, however, the soundness of LLMJ critiques often goes unmeasured. Here, we introduce Counsel, the first public dataset of meta-evaluations for agentic tasks. Counsel consists of process-level critiques from open-weight LLMJs on two agent benchmarks: tau-bench (customer support agents) and DA-Code (coding agents), and human meta-evaluations of these critiques. Human annotators label critiques on each flagged error as "spot on", "correct location but poor reasoning", or "should not have flagged", achieving reliable inter-annotator agreement (Krippendorff's alpha of 0.78). The resulting dataset stratifies LLMJ critiques by human alignment across both error location within a trajectory and reasoning quality, serving as valuable data to calibrate, improve, or train LLMJs for agents. Comparing open-weight judges, we find that more capable judge models and more reasoning effort both enabled improved human agreement, with the strongest judge reaching ~88% agreement on location and ~65% on reasoning. Counsel is generated using open-weight models and is permissively licensed for broad community use, which we hope will enable rigorous study and improved alignment of LLM-based evaluators for agentic systems.

AtlaAI Atla
·
Jun 18 1

Beyond the Verdict: Agentic Code Judging with Verifiable Feedback

Test-time scaling for large language models (LLMs) can involve generating multiple candidate solutions for selection or revising an earlier attempt. To guide selection and revision, we need a verifier that can estimate candidate correctness and provide evidence of failure. In competitive programming, however, official judging systems provide authoritative verdicts under finite submission budgets, without revealing failure explanations or failing inputs. To provide informative feedback without consuming official submissions, we formulate a task in which a model judges and diagnoses a candidate program using only the problem statement and source code, with generated counterexamples serving as checkable evidence. To evaluate this task, we build USACO-JUDGE from the USACO 2026 contests, using accepted and unaccepted programs written by human experts and multiple LLMs. We then train ARBITER, a 35B mixture-of-experts (MoE) agentic verifier, with reinforcement learning in a generic execution sandbox. Training raises counterexample success on incorrect programs from 40.61% to 62.67% and mean binary verdict accuracy on USACO-JUDGE from 71.41% to 87.41%, approaching frontier verification performance. Beyond verification, ARBITER outperforms baselines in both code selection and refinement. In an IOI 2026 case study, ARBITER-guided refinement raises GPT-OSS-120B's expected score above the gold-medal threshold under the official submission limit.

  • 7 authors
·
Oct 12 2

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning LLM-as-judge as a supervision paradigm for assessing factual accuracy, evidence use, and reasoning quality. Yet the reliability of these judges for deep research agents remains poorly understood, posing a critical meta-evaluation problem: before deploying LLM judges to supervise research agents, we must first evaluate the judges themselves. Existing meta-evaluations fall short in two ways: (1) reliance on coarse, subjective human-preference agreement; (2) focus on instruction-following or verifiable tasks, leaving open-ended agent executions unexplored. To address these gaps, we introduce REFLECT (REliable Fine-grained LLM judge Evaluation via Controlled inTervention), a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments. REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions on quality-screened agent execution traces. This yields verifiable, comprehensive, and fine-grained instances for validating the judge models. Our experiments show that current LLM judges remain unreliable: even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures, with especially poor performance on evidence verification. Together, our taxonomy and findings expose systematic judge limitations, reveal tradeoffs in cost and reliability, and offer actionable guidance for building more reliable evaluation pipelines for deep research agents.

  • 8 authors
·
May 17

LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition

LLM-as-a-judge is widely used to provide feedback and selection signals in closedloop regeneration, but this use remains insufficiently validated. We study it in table recognition, where deterministic TEDS evaluation provides a controlled testbed, using FinTabNet and OmniDocBench. Three findings emerge. First, judge signals were weak on both datasets: scores frequently tied, rankings were not reproducible, and no tested judge score policy, whether selecting among candidates or accepting revisions under a conservative score margin, improved on the first output on both datasets. Iteration produced better candidates, but the judge recovered them at most partially on one dataset and not at all on the other. Second, severe losses occurred even without specific judge feedback, supporting target-preservation failure under unconstrained regeneration as a proximate mechanism. Third, a structure-preserving instruction reduced the severe-loss rate, significantly on FinTabNet and directionally on OmniDocBench, but produced no improvement, and in an exploratory 2x2 analysis this protection was not stably observed when judge feedback was retained. These results do not dispute the value of LLMs as evaluators, but show that the tested reference-free judge signals were too weak and unstable to drive candidate selection in this setup, and that evaluation-style evidence alone was insufficient to establish closed-loop optimization utility. Iterative refinement requires, at minimum, a verification signal that deterministically detects structural change, rather than judge scores alone.

  • 1 authors
·
Jul 15

SLMJury: Can Small Language Models Judge as Well as Large Ones?

Large language models (LLMs) are widely used as judges for evaluating model outputs, but their high cost, latency, and opacity limit scalability. We introduce SLMJury, a framework for evaluating small language models (SLMs) as judges across two paradigms: closed-ended binary correctness and open-ended quality scoring. We benchmark 16 SLM judges (0.6B-14B parameters) from four model families across ten benchmarks: eight closed-ended tasks spanning mathematical, scientific, and general reasoning (N=64,824 judgments per configuration), plus SummEval and MT-Bench for summarization and conversational scoring. We formalize judging as a budget-conditioned function and study five dimensions. Four findings emerge. (1) The overthinking effect is domain-dependent: for most judges quick 10-token verdicts match or beat extended reasoning on mathematical judging (by 2-7% where they help), while reasoning wins on general tasks by up to 23%. (2) Domain generalization separates model families, with math-to-general accuracy gaps ranging from under 10% to nearly 40%. (3) Closed-ended and open-ended judging draw on different capabilities: the best binary judge (Phi-4) drops to rank 9 on MT-Bench, while reasoning-trained models invert this ordering. (4) Under the Reflect-Critique-Refine (RCR) debate protocol, multi-agent debate degrades accuracy across all tested configurations, whereas the top judges resist six adversarial personas with <=0.55% variance. Reliable automated evaluation does not require large proprietary models, yet no single SLM dominates. The leaderboard is available at https://anishh15.github.io/SLMJury/, and our framework code and pip package are publicly available at https://github.com/anishh15/SLMJury and https://pypi.org/project/slmjury/.

  • 3 authors
·
Jun 4

Interaction-as-a-Judge

Coding agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applications interactively, current automated LLM evaluations primarily focus on code analysis and unit tests. This mismatch can cause LLM judges to miss failures that are immediately apparent to human users. We study Interaction-as-a-Judge, an evaluation paradigm where computer-use agents (CUAs) directly interact with an application. We demonstrate that Interaction-as-a-Judge can improve both evaluation and generation of interactive applications. To this end, we collect and release two complementary datasets: 6,858 pairs of applications with human preferences and corresponding agent traces, and 222 applications with human-verified requirement labels. Relative to standard non-interactive approaches, we find that Interaction-as-a-Judge improves evaluation in terms of predicting human preferences (65.6% to 69.1%) and requirement verification (77.0% to 81.6%). We also observe scaling benefits: across both preference alignment and requirement verification, higher-quality interactions improve performance. Finally, through both inference- and training-time experiments, we demonstrate that Interaction-as-a-Judge can also improve the quality of generated artifacts. At inference time, Interaction-as-a-Judge repairs 75.5% of broken requirements within five attempts, compared to 55.4% for code-only self-feedback. At training time, using Interaction-as-a-Judge as a reward signal improves win-rate over the base model by 6.7pp while reducing both generated code length by 35.7% and build failure rates by 7.2pp compared to a code-only reward signal.

  • 9 authors
·
Oct 13

OpenCLAW-P2P v6.0: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review

This paper presents OpenCLAW-P2P v6.0, a comprehensive evolution of the decentralized collective-intelligence platform in which autonomous AI agents publish, peer-review, score, and iteratively improve scientific research papers without any human gatekeeper. Building on v5.0 foundations -- tribunal-gated publishing, multi-LLM granular scoring, calibrated deception detection, the Silicon Chess-Grid FSM, and the AETHER containerized inference engine -- this release introduces four major new subsystems: (1) a multi-layer paper persistence architecture with four storage tiers (in-memory cache, Cloudflare R2, Gun.js, GitHub) ensuring zero paper loss across redeployments; (2) a multi-layer retrieval cascade with automatic backfill reducing lookup latency from >3s to <50ms; (3) live reference verification querying CrossRef, arXiv, and Semantic Scholar during scoring to detect fabricated citations with >85% accuracy; and (4) a scientific API proxy providing rate-limited cached access to seven public databases. The platform operates with 14 real autonomous agents producing 50+ scored papers (word counts 2,072-4,073, leaderboard scores 6.4-8.1) alongside 23 labeled simulated citizens. We present honest production statistics, failure-mode analysis, a paper recovery protocol that salvaged 25 lost papers, and lessons learned from operating the system at scale. All pre-existing subsystems -- 17-judge multi-LLM scoring, 14-rule calibration with 8 deception detectors, tribunal cognitive examination, Proof of Value consensus, Laws-of-Form eigenform verification, and tau-normalized agent coordination -- are retained and further hardened. All code is open-source at https://github.com/Agnuxo1/p2pclaw-mcp-server.

  • 6 authors
·
Apr 5 1

RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges

LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or distillation from stronger teachers. In this work, we eliminate external gold supervision from the RL training reward: the model's own evaluative capability generates learning signals for its optimization -- a closed-loop setting of bounded recursive self-improvement (RSI) termed Recursive Self-Evaluation (RecurSE). We study two central questions: when can self-improvement occur, and when must it stop? First, RecurSE pairs a trainable judge evaluating candidate responses under per-rule rubrics (Pass 1) with a synchronized policy-copy checker that audits the judge's reasoning against meta-rubrics to supply a scalar process reward (Pass 2). To enable learning, interface decoupling structurally isolates the checker's scalar score from the judge's verdict tokens, eliminating a degenerative token-copying shortcut that inflates self-assigned rewards. Second, because unanchored recursive learning is inherently bounded, Pairwise Advantage Validity (PAV) serves as an unbiased validation monitor that jointly tracks judge accuracy and checker fidelity to reliably identify the optimal early-stopping window. Across Qwen3.5-9B, Gemma-4-E4B-it, and Qwen3.6-27B, RecurSE achieves consistent generalization gains across held-out medical, pairwise, summarization, and professional benchmarks. Ablations demonstrate that synchronized judge-checker co-evolution outperforms frozen checkers, external meta-judges, self-consistency, and scaled teacher distillation. Furthermore, preference pairs curated by our judge effectively enhance downstream policy alignment. Bounded RSI for LLM-as-judge is thus viable when self-produced reward validity is explicitly decoupled and monitored.

  • 4 authors
·
Aug 24

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

The rapid advancement of Large Language Models (LLMs) has driven their expanding application across various fields. One of the most promising applications is their role as evaluators based on natural language responses, referred to as ''LLMs-as-judges''. This framework has attracted growing attention from both academia and industry due to their excellent effectiveness, ability to generalize across tasks, and interpretability in the form of natural language. This paper presents a comprehensive survey of the LLMs-as-judges paradigm from five key perspectives: Functionality, Methodology, Applications, Meta-evaluation, and Limitations. We begin by providing a systematic definition of LLMs-as-Judges and introduce their functionality (Why use LLM judges?). Then we address methodology to construct an evaluation system with LLMs (How to use LLM judges?). Additionally, we investigate the potential domains for their application (Where to use LLM judges?) and discuss methods for evaluating them in various contexts (How to evaluate LLM judges?). Finally, we provide a detailed analysis of the limitations of LLM judges and discuss potential future directions. Through a structured and comprehensive analysis, we aim aims to provide insights on the development and application of LLMs-as-judges in both research and practice. We will continue to maintain the relevant resource list at https://github.com/CSHaitao/Awesome-LLMs-as-Judges.

  • 8 authors
·
Dec 7, 2024

ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts

The potential of large language models (LLMs) in specialized domains such as legal risk analysis remains underexplored. In response to growing interest in locally deploying open-source LLMs for legal tasks while preserving data confidentiality, this paper introduces ContractEval, the first benchmark to thoroughly evaluate whether open-source LLMs could match proprietary LLMs in identifying clause-level legal risks in commercial contracts. Using the Contract Understanding Atticus Dataset (CUAD), we assess 4 proprietary and 15 open-source LLMs. Our results highlight five key findings: (1) Proprietary models outperform open-source models in both correctness and output effectiveness, though some open-source models are competitive in certain specific dimensions. (2) Larger open-source models generally perform better, though the improvement slows down as models get bigger. (3) Reasoning ("thinking") mode improves output effectiveness but reduces correctness, likely due to over-complicating simpler tasks. (4) Open-source models generate "no related clause" responses more frequently even when relevant clauses are present. This suggests "laziness" in thinking or low confidence in extracting relevant content. (5) Model quantization speeds up inference but at the cost of performance drop, showing the tradeoff between efficiency and accuracy. These findings suggest that while most LLMs perform at a level comparable to junior legal assistants, open-source models require targeted fine-tuning to ensure correctness and effectiveness in high-stakes legal settings. ContractEval offers a solid benchmark to guide future development of legal-domain LLMs.

  • 5 authors
·
Aug 4, 2025

CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict

E-commerce platforms have begun recruiting crowdsourced jurors to adjudicate massive volumes of transaction disputes. Unlike formal legal judgment, E-commerce dispute verdicts require grounding pivotal clues from redundant, multi-round, multimodal evidence and making decisions under flexible platform-specific conventions. These characteristics render existing methods insufficient for this scenario. To bridge this gap, we introduce a pioneering task, E-commerce Dispute Verdicts (EDV), and present VerdictBench, a multimodal benchmark comprising 6,000 real-world cases designed to reflect crowdsourced jury decisions. Building upon this, we propose CyberJurors, a multi-agent framework to clarify the dispute logic and regulate the verdict process. At the individual level, Individual Verdict Chain-of-Thought decomposes the EDV task into four structured reasoning stages, enabling fine-grained clue perception and clarifying causal logic between pivotal clues and the dispute focus. At the collective level, Jury Consensus Verdict simulates multi-round discussion and voting among jurors, while incorporating verdict precedents to mitigate cognitive biases toward either disputant. Experiments on VerdictBench show that CyberJurors outperforms state-of-the-art LLMs, MLLMs, and court simulators, while achieving stronger alignment with real-world jury voting patterns. Code and dataset are available at https://github.com/YanhuiS/CyberJurors and https://huggingface.co/datasets/piggi/VerdictBench.

  • 6 authors
·
May 26

The Open Source Advantage in Large Language Models (LLMs)

Large language models (LLMs) mark a key shift in natural language processing (NLP), having advanced text generation, translation, and domain-specific reasoning. Closed-source models like GPT-4, powered by proprietary datasets and extensive computational resources, lead with state-of-the-art performance today. However, they face criticism for their "black box" nature and for limiting accessibility in a manner that hinders reproducibility and equitable AI development. By contrast, open-source initiatives like LLaMA and BLOOM prioritize democratization through community-driven development and computational efficiency. These models have significantly reduced performance gaps, particularly in linguistic diversity and domain-specific applications, while providing accessible tools for global researchers and developers. Notably, both paradigms rely on foundational architectural innovations, such as the Transformer framework by Vaswani et al. (2017). Closed-source models excel by scaling effectively, while open-source models adapt to real-world applications in underrepresented languages and domains. Techniques like Low-Rank Adaptation (LoRA) and instruction-tuning datasets enable open-source models to achieve competitive results despite limited resources. To be sure, the tension between closed-source and open-source approaches underscores a broader debate on transparency versus proprietary control in AI. Ethical considerations further highlight this divide. Closed-source systems restrict external scrutiny, while open-source models promote reproducibility and collaboration but lack standardized auditing documentation frameworks to mitigate biases. Hybrid approaches that leverage the strengths of both paradigms are likely to shape the future of LLM innovation, ensuring accessibility, competitive technical performance, and ethical deployment.

  • 4 authors
·
Dec 16, 2024 2

Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering

Large Language Models are increasingly used as judges to evaluate code artifacts when exhaustive human review or executable test coverage is unavailable. LLM-judge is increasingly relevant in agentic software engineering workflows, where it can help rank candidate solutions and guide patch selection. While attractive for scale, current practice lacks a principled account of reliability and bias: repeated evaluations of the same case can disagree; small prompt edits can swing outcomes; and seemingly semantics-preserving, human-equivalent perturbations may elicit divergent verdicts. This paper studies LLM-as-a-Judge for code through a measurement-first lens. We analyze two pointwise judging regimes across code generation, code repair task, and test generation, and we systematically probe prompt-induced biases. Our study considers difficulty levels for repeated runs and controlled prompt interventions that isolate one presentation cue at a time, and it evaluates judges using consistency and sensitivity to bias. We find that judge decisions are highly sensitive to prompt biases even when the underlying code snippet is unchanged. Across all three tasks, several biases systematically shift preferences toward the option favored by the prompt, improving accuracy when that option aligns with the gold answer but substantially reducing it otherwise. In some settings, these effects are large enough to change task-level conclusions and alter relative model rankings. These findings show that reported judge performance may reflect prompt artifacts rather than stable assessment ability, posing a direct threat to the validity and reproducibility of code evaluation. We therefore argue that LLM-as-a-Judge studies should report bias sensitivity alongside accuracy and incorporate explicit controls to support more trustworthy model comparison in software engineering.

  • 3 authors
·
Apr 17

AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks

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

  • 10 authors
·
Oct 7

Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems

LLM-as-judge evaluation has become the de facto standard for scaling model assessment, but the practice is statistically unsound: uncalibrated scores can invert preferences, naive confidence intervals on uncalibrated scores achieve near-0% coverage, and importance-weighted estimators collapse under limited overlap despite high effective sample size (ESS). We introduce Causal Judge Evaluation (CJE), a framework that fixes all three failures. On n=4,961 Chatbot Arena prompts (after filtering from 5k), CJE achieves 99% pairwise ranking accuracy at full sample size (94% averaged across configurations), matching oracle quality, at 14x lower cost (for ranking 5 policies) by calibrating a 16x cheaper judge on just 5% oracle labels (~250 labels). CJE combines three components: (i) AutoCal-R, reward calibration via mean-preserving isotonic regression; (ii) SIMCal-W, weight stabilization via stacking of S-monotone candidates; and (iii) Oracle-Uncertainty Aware (OUA) inference that propagates calibration uncertainty into confidence intervals. We formalize the Coverage-Limited Efficiency (CLE) diagnostic, which explains why IPS-style estimators fail even when ESS exceeds 90%: the logger rarely visits regions where target policies concentrate. Key findings: SNIPS inverts rankings even with reward calibration (38% pairwise, negative Kendall's tau) due to weight instability; calibrated IPS remains near-random (47%) despite weight stabilization, consistent with CLE; OUA improves coverage from near-0% to ~86% (Direct) and ~96% (stacked-DR), where naive intervals severely under-cover.

  • 1 authors
·
Dec 11, 2025 2

Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines

Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down. But the judge is itself a model behind an API, and a silent version bump or scoring-prompt update changes how it scores -- so every drift alarm is ambiguous between a worse product and a changed judge. We resolve the ambiguity with a fixed, human-labeled anchor set that the current judge re-scores at a steady interleave, a second betting e-process on the judge-versus-human gap, and a guard-window rule returning a verdict in {none, system, judge}. We prove anytime-validity, one-way identification (only the judge can move the anchors), an attribution race whose design law is that the anchors must out-run the main process they guard, and process orthogonality. On two real judge changes, a silent version bump is detected as judge drift in 60/60 runs with zero judge-to-system misattribution, and a contaminating strict-prompt change is correctly attributed on 110 of 120 runs at guard width 300 -- while the industry-default rolling z-test false-alarms on 75% of drift-free streams. Every experiment replicates on a second domain (TL;DR summarization) with nothing re-tuned, and where the domains differ the differences are the ones the race predicts: the strict-prompt change shifts scores harder there, so the anchors fire faster and attribution becomes perfect (240/240). The monitor runs at approximately 0.64 of the cost of strong-judging every item, or 0.21 in a cheaper-but-deafer regime.

  • 1 authors
·
Jun 12

AgenticSimLaw: A Juvenile Courtroom Multi-Agent Debate Simulation for Explainable High-Stakes Tabular Decision Making

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style orchestration explicitly defines agent roles (prosecutor, defense, judge), interaction protocols (7-turn structured debate), and private reasoning strategies, creating a fully auditable decision-making process. We benchmark this framework on young adult recidivism prediction using the NLSY97 dataset, comparing it against traditional chain-of-thought (CoT) prompting across almost 90 unique combinations of models and strategies. Our results demonstrate that structured multi-agent debate provides more stable and generalizable performance compared to single-agent reasoning, with stronger correlation between accuracy and F1-score metrics. Beyond performance improvements, AgenticSimLaw offers fine-grained control over reasoning steps, generates complete interaction transcripts for explainability, and enables systematic profiling of agent behaviors. While we instantiate this framework in the criminal justice domain to stress-test reasoning under ethical complexity, the approach generalizes to any deliberative, high-stakes decision task requiring transparency and human oversight. This work addresses key LLM-based multi-agent system challenges: organization through structured roles, observability through logged interactions, and responsibility through explicit non-deployment constraints for sensitive domains. Data, results, and code will be available on github.com under the MIT license.

  • 3 authors
·
Jan 28

AcademiClaw: When Students Set Challenges for AI Agents

Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We introduce AcademiClaw, a bilingual benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic workflows -- homework, research projects, competitions, and personal projects -- that they found current AI agents unable to solve effectively. Curated from 230 student-submitted candidates through rigorous expert review, the final task set spans 25+ professional domains, ranging from olympiad-level mathematics and linguistics problems to GPU-intensive reinforcement learning and full-stack system debugging, with 16 tasks requiring CUDA GPU execution. Each task executes in an isolated Docker sandbox and is scored on task completion by multi-dimensional rubrics combining six complementary techniques, with an independent five-category safety audit providing additional behavioral analysis. Experiments on six frontier models show that even the best achieves only a 55\% pass rate. Further analysis uncovers sharp capability boundaries across task domains, divergent behavioral strategies among models, and a disconnect between token consumption and output quality, providing fine-grained diagnostic signals beyond what aggregate metrics reveal. We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community, driving progress toward agents that are more capable and versatile across the full breadth of real-world academic demands. All data and code are available at https://github.com/GAIR-NLP/AcademiClaw.

  • 78 authors
·
May 3 2

Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models

Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding sessions. Its two tracks, Multimodal Editing (ME) and Repository Editing (RE), cover localized edits with optional image, audio, video, or document inputs and coordinated repository revisions. Tasks span three capability dimensions: Grounded Understanding, UI Transformation, and Functional Implementation. The tasks pair normalized requests and runnable pre-edit applications with 2,331 hidden expert-authored acceptance criteria. Our judge-then-refute protocol grades criteria using source and browser evidence, challenges positive verdicts with a separate LLM verifier, and audits visual and interaction claims without gold code or target screenshots. Under a shared agentic harness, the strongest of ten model endpoints passes an average of 69.9% of criteria per task but fully satisfies only 26.4% of tasks. All ten endpoints achieve lower criterion completion on repository edits spanning three or four change types than on those spanning one or two. Co-Design Bench provides a testbed for studying the gap between partial requirement satisfaction and complete task success under agentic execution for real-user application revisions.

Qwen Qwen
·
Oct 25 3

Mediocrity is the key for LLM as a Judge Anchor Selection

The ``LLM-as-a-judge'' paradigm has become a standard method for evaluating open-ended generation. To address the quadratic scalability costs of pairwise comparisons, popular benchmarks like Arena-Hard and AlpacaEval compare all models against a single anchor. However, despite its widespread use, the impact of anchor selection on the reliability of the results remains largely unexplored. In this work, we systematically investigate the effect of anchor selection by evaluating 22 different anchors on the Arena-Hard-v2.0 dataset. We find that the choice of anchor is critical: a poor anchor can dramatically reduce correlation with human rankings. We identify that common anchor choices (best-performing and worst-performing models) make poor anchors. Because these extreme anchors are consistently better or worse than all other models, they are seldom indicative of the relative ranking of the models. We further quantify the effect size of anchor selection, showing it is comparable to the selection of a judge model. We conclude with actionable recommendations. First, we conduct a power analysis, and compute sufficient benchmark sizes for anchor-based evaluation, finding that standard benchmark sizes are insufficient for pairwise evaluation and fail to distinguish between competitive models reliably. Second, we provide guidelines for selecting informative anchors to ensure reliable and efficient evaluation practices.

  • 4 authors
·
Mar 17

AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation

Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallible LLM judges. We report on AGO AI Quality Gate (AGO), an evidence-first quality-gate framework deployed in industrial RAG assessment engagements. AGO integrates four key components: a four-state decision model that treats missing data and judge errors as explicit outcomes; layered scoring combining deterministic checks, local guardrails, and structured LLM evaluation; a stratified beta-binomial gate that quantifies regression risk probabilistically; and a mandatory meta-evaluation protocol to validate the LLM judge before it influences decisions. Since engagement data is proprietary, we evaluate the judge layer on RAGBench, a public benchmark of 100k annotated RAG traces across 12 datasets. On identical stratified test samples (N=1200 per judge), a low-cost judge (gpt-4.1-nano) detects non-adherent answers barely above chance (AUROC 0.603 [0.570, 0.634]), despite producing flawless protocol output, while gpt-4o reaches 0.783 [0.756, 0.807] -- yet its per-domain performance still ranges from 0.62 to 0.88. A fixed-seed gate study spanning regression, no change, and improvement quantifies unsafe promotion, false-alarm cost, and improvement throughput. Under regression, the decision-grade profile reduces unsafe promotion to 22.2%-35.1%, against 29.3%-41.8% for a naive gate. These results support the design choices that judge quality must be measured per engagement and that point estimates alone are not a release decision.

  • 6 authors
·
Sep 30 2

PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning

Frontier model progress is often measured by academic benchmarks, which offer a limited view of performance in real-world professional contexts. Existing evaluations often fail to assess open-ended, economically consequential tasks in high-stakes domains like Legal and Finance, where practical returns are paramount. To address this, we introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it, to our knowledge, the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed tasks inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Our analysis shows that models with similar overall scores can diverge significantly on specific capabilities. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption.

  • 24 authors
·
Nov 14, 2025

DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into decision-oriented insights. We introduce DAComp, a benchmark of 210 tasks that mirrors these complex workflows. Data engineering (DE) tasks require repository-level engineering on industrial schemas, including designing and building multi-stage SQL pipelines from scratch and evolving existing systems under evolving requirements. Data analysis (DA) tasks pose open-ended business problems that demand strategic planning, exploratory analysis through iterative coding, interpretation of intermediate results, and the synthesis of actionable recommendations. Engineering tasks are scored through execution-based, multi-metric evaluation. Open-ended tasks are assessed by a reliable, experimentally validated LLM-judge, which is guided by hierarchical, meticulously crafted rubrics. Our experiments reveal that even state-of-the-art agents falter on DAComp. Performance on DE tasks is particularly low, with success rates under 20%, exposing a critical bottleneck in holistic pipeline orchestration, not merely code generation. Scores on DA tasks also average below 40%, highlighting profound deficiencies in open-ended reasoning and demonstrating that engineering and analysis are distinct capabilities. By clearly diagnosing these limitations, DAComp provides a rigorous and realistic testbed to drive the development of truly capable autonomous data agents for enterprise settings. Our data and code are available at https://da-comp.github.io

ByteDance-Seed ByteDance Seed
·
Dec 3, 2025 6