AgentJudgeBench is a new benchmark that evaluates the reliability of large language model (LLM) judges on agentic tool‑calling tasks involving workflow directed acyclic graphs (DAGs). It contains 3,808 instances across six DAG topologies and three difficulty tiers, tested with five generators (3B–70B open‑weight models and GPT‑5.4) and six judges (20B to frontier scale) under both paired‑with‑and‑without‑ground‑truth conditions. The study finds that judge alignment degrades with task difficulty, ground‑truth exposure can sometimes hurt alignment, and structured evaluation rubrics provide modest improvements, revealing a structural ceiling that model capacity alone cannot surpass.
By Abhigya Verma, Amit Kumar Saha, Seganrasan Subramanian, Sai Harshitha Aluru
The paper evaluates hard‑gate candidacy for validators in a deployed generative‑agent system by measuring how well each validator’s firing separates successful from failed builds. Across 13 validators and thousands of builds, only a few checks show statistically significant separation, while many fail to distinguish or never fire. The study highlights that skipped checks are recorded as passes, limiting detectable failure rates and underscoring the need for clearer evaluation records.
By Xin Xu
arXiv:2608. 07813v1 Announce Type: new Abstract: An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships.
By Yiyao Zhang, Diksha Goel, Hussain Ahmad, Shixun Huang, Jun Shen
arXiv:2606. 13685v1 Announce Type: cross Abstract: LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized.
By Abel Yagubyan
The paper introduces DIB-Bench, a benchmark that exposes deployment‑integrity blindness in large language model (LLM) evaluation by testing 7,560 scored examples across six tamper types and a range of evaluators from regex scorers to GPT‑5‑nano. It shows that stronger evaluators are more likely to accept tampered outputs—mean acceptance rises from 88.6% for rule‑based scorers to 94.1% for GPT‑5‑nano—and that certain trigger‑conditional tampering can produce harmful outputs in 48–100% of cases, increasing with model capability. The study also demonstrates that output‑only evaluation cannot detect tampering with zero output shift, while a manifest‑hash identity channel can detect it with zero samples, and proposes a graded deployment‑identity descriptor for evaluation reports.
By Jianchang Su, Dawei Xiang, Yifan Zhang, Wei Zhang
VERITYGATE is a four‑gate framework that checks whether LLM‑generated narrations adhere to a fixed schema of declared evidence IDs, entities, numbers, and claim types, rather than verifying every fact in the prose. In experiments with GPT‑4o‑mini, Llama‑3.3‑70B, and Claude Sonnet 4.6 on 900 grounded‑ungrounded pairs, the framework identified high failure rates (up to 80.3% for mini claims) and demonstrated that a single repair pass can improve claim survival rates. The authors also provide code, data, and preliminary human studies to validate the rules and highlight gaps between schema compliance and correct prose.
"whyItMatters":"The framework offers a systematic way to evaluate and improve the faithfulness of LLM explanations to structured evidence, revealing significant failure rates and the impact of repair strategies."
By Sachin Gupta
The paper evaluates a production text‑to‑SQL pipeline that uses an LLM as a judge, finding that the deployed gpt‑4o‑mini judge agrees with human annotators only weakly (Cohen’s kappa 0.04 on a disagreement‑enriched set and 0.42 on a random spot‑check). The authors identify a specific failure mode, GRADE‑HALLUCINATION, responsible for most over‑flags, and demonstrate that a self‑hosted Qwen3.6‑27B model achieves substantially higher agreement (kappa 0.72) at a much lower cost. They also show that ensembling judges does not improve performance, and that their audit method flags a significant portion of out‑of‑domain SQLs as potential issues.
By Haowei Liu, Hsin-Tai Wu, Yi Fang
arXiv:2504. 15610v4 Announce Type: replace Abstract: Fine-tuning a 7B language model for specialized advising is attractive in resource-constrained settings, but multi-epoch runs routinely exceed the wall-clock limits of the free-tier GPUs (Kaggle, Colab) such users rely on.
By Md Millat Hosen
arXiv:2610.32986v1 Announce Type: cross
Abstract: Automated research pipelines increasingly rely on fixed LLM judges to rank, filter, and revise proposals, yet these judges are routinely replaced by...
By Guijia Zhang, Harry Yang
arXiv:2610.15710v1 Announce Type: new
Abstract: Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim. Benchmark labels for this step mark a pair...
By Xupeng Chen, Chenqian Le
SiLR introduces a structure‑preserving admission and process reward mechanism for large language model (LLM) tool agents. Unlike traditional scalar‑score gates that can trap agents in plateau trajectories, SiLR shadow‑executes each proposal and admits it based on a product order over branch‑level violation states, ensuring safe and recoverable actions. Experiments on Gym‑ANM and CityLearn benchmarks show SiLR consistently recovers all multi‑action episodes and outperforms scalar gates, while also providing a robust reward signal for policy learning.
By Chenyu Zhou, Qiliang Jiang, Shuning Wu, Xu Zhou
arXiv:2607. 07405v1 Announce Type: new Abstract: Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully.
By Vikas Reddy, Sumanth Reddy Challaram, Abhishek Basu