arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.
By Bhaskar Gurram
arXiv:2609.35889v1 Announce Type: cross
Abstract: Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing...
By Xiaoyu Xu, Zi Liang, Minxin Du, Qipeng Xie, Qingqing Ye, Yuyuan Li, Haibo Hu
arXiv:2607. 04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded.
By Jaber Jaber, Osama Jaber
The paper introduces VerifierBench, a benchmark comprising 222 tasks from six agent benchmarks and 4,993 hidden test cases designed to evaluate the generation of executable verifiers by large language model agents. It presents Verifier4Verifier (V4V), a six-check audit that screens source verifiers and test suites, and reports that across 19 models, normalized balanced accuracy ranges from 10.6 to 62.1, with generated verifiers more reliably rejecting invalid solutions than accepting valid ones. Case studies highlight that many false rejections stem from verifiers that accept no tested solution, revealing unsupported assumptions about solution formats, tool use, and code changes that exclude valid solutions, and underscore the need to test both acceptance of correct solutions and other permissible solutions.
By Jianing Yin, Ziyi Chen, Hao Wang, Yiyou Sun, Zijian Jin, Dawn Song, Daoan Zhang
The paper reports a preregistered audit of language‑model judges used as measurement instruments, revealing that the assumption that a model’s responses remain stable over time is invalid. Across nearly 53,000 audited requests, repeat rankings and byte‑identical replays fell far below required reliability thresholds, with three identified mechanisms—label‑to‑meaning bias, candidate gaps below the noise floor, and input permutation noise—explaining the discrepancy. The study proposes a three‑level snapshot‑identity framework, eight design rules, and a reporting checklist to prevent such reliability failures in future evaluations.
By Haoyaun Zhu, Jie Zhang
The paper investigates the reliability of language‑model judges used as measurement instruments on shared endpoints. Through two preregistered audits of 52,988 requests, the authors found that repeat rankings and byte‑identical replays fell far short of required thresholds, revealing significant instability. They identify three mechanisms—label‑to‑meaning bias, candidate gaps below the noise floor, and input permutation noise—that explain the gap, and propose a snapshot‑identity ladder, design rules, and a reporting checklist to mitigate such failures.
The paper introduces mutation analysis as a metric for evaluating GPU‑kernel benchmark oracles, injecting over ten thousand faults into verified CUDA implementations of 188 KernelBench problems. It shows that the current official checkers miss 16.9% of faults, with precision faults being especially problematic, and demonstrates that optimized test suites can achieve 98% detection with only two inputs per problem. The study also reveals flaws in existing patches and a fuzzing recipe that incorrectly rejects correct kernels 107 times.
By Mingzhe Du, Anh Tuan Luu, Dong Huang, See-Kiong Ng
arXiv:2606. 20128v1 Announce Type: cross Abstract: Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks.
By Dipankar Sarkar
The paper introduces SpecAgent, a protocol that lets a strong language model act as a reviewer rather than a generator for tool‑using agents. A weaker model drafts steps, executing read‑only tool calls to ground its proposals, while the strong model verifies the draft in a single prefill pass, committing the longest valid prefix and repairing any rejected step. Experiments on benchmarks show SpecAgent achieves near‑strong‑model performance while cutting memory traffic, wall time, and token generation.
By Zilin Wang, Yinhong Liu, Chao Chen, Qun Liu, Zhijiang Guo
AgentAudit is an open, extensible framework that evaluates the full lifecycle of AI agents, assessing planning, tool selection, execution, memory, and reasoning across ten dimensions such as instruction integrity, security, and alignment. Unlike existing benchmarks that focus on single aspects, AgentAudit analyzes the entire execution trace to attribute failures to specific stages. The framework was tested on five large language models, revealing significant differences in trustworthiness even among models with similar task‑completion performance.
By Shrey Nag, Sachita, Abhishek Kumar Singh, Lipi Goel, Rajeshwar Singh Janwar
arXiv:2609.24165v1 Announce Type: new
Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound...
By Pawan K. Tripathi, Hemant Sharma, Andrew Chuang, Mathew J. Cherukara
arXiv:2610.02267v1 Announce Type: new
Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input...
By Jiawei Li