The paper introduces TraceTrial-Bench, a benchmark that evaluates the reliability of AI agent harnesses across seven components—context, execution, governance, lifecycle, observability, tools, and verification—using 95 expert-level tasks with executable or state-based ground truth. It employs a Trajectory Tracing module to record agent execution, a two-layer evaluation framework to separately assess agent performance and harness reliability, and a Multi-source Evidence Acquisition module to gather evidence for LLM-based evaluation. The benchmark’s analysis of 3,420 runs across four harnesses and nine models shows harness scores between 59.8% and 72.0%, with 31.1% of runs succeeding despite failing at least one harness criterion, highlighting the need for auditable and reproducible harness evaluation.
By Zhiyong Cao, Hengjie Zhu, Yongxin Wang, Xuchen Li, Jintao Li, Shuxia Liu, Dunqiang Liu, Bo Wang, Kairan Zhang, Cong Lin, JiangDi Yu, Siyuan Liu, Sijia Yao, Yi-Liang Wei, Lingxu Ma, Aijia Wang, Anxin Chen, Zixian Wei, Xiang Ruan, Ruizhi Xu, Ruqian Shi, Baihua Xiao, Sicheng Zhou
arXiv:2605. 21347v3 Announce Type: replace Abstract: Diagnosing failures in LLM agents remains largely manual.
By Akshay Manglik, Apaar Shanker, Kaustubh Deshpande, Jason Qin, Yash Maurya, Veronica Chatrath, Vijay S. Kalmath, Levi Lentz, Yuan Xue
arXiv:2606. 09498v3 Announce Type: replace Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment.
By Hangfan Zhang, Shao Zhang, Kangcong Li, Chen Zhang, Yang Chen, Yiqun Zhang, Lei Bai, Shuyue Hu
arXiv:2608. 07346v1 Announce Type: new Abstract: With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains.
By Haoning Wang, Mingxun Zhang, Chenyue Yu, Yingjun Shang, Xia Hu, Guanchu Wang, Na Zou
arXiv:2608. 07346v2 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains.
By Haoning Wang, Mingxun Zhang, Chenyue Yu, Yingjun Shang, Xia Hu, Guanchu Wang, Na Zou
Harness-Bench is a diagnostic benchmark that evaluates how different harness configurations affect LLM agent performance in realistic workflows. It tests 106 sandboxed offline tasks across multiple model backends, recording artifacts, execution traces, and usage statistics to analyze completion, process quality, efficiency, and failure behavior. The study finds significant variation in outcomes across model-harness pairings, indicating that agent capability should be reported at the configuration level rather than solely by the base model.
By Yilun Yao, Xinyu Tan, Chao-Hsuan Liu, Yaoming Li, Zhengyang Wang, Zongwei Lv, Wenhan Yu, Zhewen Tan, Yuxuan Tian, Lin Sun, Xiangzheng Zhang, Guangxiang Zhao, Tong Yang
Automated root cause analysis (RCA) with large language models (LLMs) has drawn growing attention. Today, SREs typically automate RCA with LLMs in one of two ways: directly using a general-purpose age...
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.
By Kunlun Zhu, Xuyan Ye, Yibo Li, Cheng Qian, Beibin Li, Heng Ji
arXiv:2602.02475v2 Announce Type: replace
Abstract: AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy...
By Shraddha Barke, Arnav Goyal, Alind Khare, Avaljot Singh, Suman Nath, Chetan Bansal
The paper introduces BenchGuard, a framework that uses advanced language models to audit execution-based agent benchmarks. BenchGuard systematically cross-verifies benchmark artifacts through structured LLM protocols, optionally incorporating agent solutions or execution traces for deeper diagnostics. In tests on ScienceAgentBench and BIXBench Verified-50, BenchGuard uncovered numerous author-confirmed and expert-identified issues, including fatal errors that made tasks unsolvable, and demonstrated cost-effective auditing for complex bioinformatics tasks.
By Xinming Tu (Minta), Tianze Wang (Minta), Yingzhou (Minta), Lu, Kexin Huang, Yuanhao Qu, Sara Mostafavi
arXiv:2607. 28591v1 Announce Type: cross Abstract: Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation.
By Haomin Qi, Xingliang Wang, Xuanqi Gao, Baihui Sang, Xin Zhang, Minghua Ma, Pengfei Gao, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
The paper presents a systematic analysis of five state‑of‑the‑art automated program repair agents, tracing their decision‑making across 500 real‑world repair tasks. It finds that while the agents perform well on simple fixes, they struggle with logic‑intensive bugs, often producing verbose, overfitted patches that pass tests without addressing root causes. Key bottlenecks identified include poor test generation, limited regression test selection, and reliance on primitive tooling without access to debuggers or advanced program analysis tools.
By Ira Ceka, Hailie Mitchell, Saurabh Pujar, Luca Buratti, Shyam Ramji, Junfeng Yang, Gail Kaiser, Baishakhi Ray