arXiv AI August 18, 2026 By Mehdi Bahrami, Kosaku Kimura, Satoshi Munakata, Satoshi Nakashima, Yu Ishikawa, Kosuke Maeda, Nao Soma, Kenichi Kobayashi, Keisuke Miyazaki, Keizo Kato, Shigeki Fukuta, Tatsuo Kumano, Nobutaka Imamura, Kevin Musgrave, Shahbaz Abdul Khader, Kwun Ho Ngan, Joe Townsend, Fayas Asharindavida, Matthieu Parizy, Akira Sakai, Yuma Ichikawa, Yang Zhao, Michiaki Takizawa, Taku Fukui, Hiroki Ohtsuji, Wei-Peng Chen, Hiromichi Kobashi

Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair

Read the original on arXiv AI →

arXiv:2608. 15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use discipline, context persistence, heterogeneous clusters, and evaluation reuse.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 12

Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents

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

llms agents benchmarks

arXiv AI

Jul 2

SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests

arXiv:2607. 00990v1 Announce Type: cross Abstract: Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue reports and code repositories.

By Yaoqi Guo, Yang Liu, Jie M. Zhang, Yun Ma, Yiling Lou, Zhenpeng Chen

llms agents benchmarks

arXiv AI

Jul 15

Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs

arXiv:2607. 12605v1 Announce Type: cross Abstract: Large language models (LLMs) have improved automated program repair (APR), but two limitations remain.

By Zhili Huang, Ling Xu, Hongyu Zhang

llms agents

arXiv AI

1d ago

Evaluating Agentic Code Repair Capabilities in Distributed Systems

arXiv:2608. 14863v1 Announce Type: cross Abstract: LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now clustering in the high-70s on SWE-bench Verified.

By Yibo Yan, Huijuan Wang, Junzhou He, Yizhuo Liang, Shaoyu Wang, Huanchen Sun, Seo Jin Park

llms agents benchmarks

arXiv AI

Jul 1

An Executable Benchmarking Suite for Tool-Using Agents

arXiv:2605. 11030v2 Announce Type: replace-cross Abstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims.

By Zhiqing Zhong, Zhijing Ye, Jiamin Wang, Xiaodong Yu

agents benchmarks

arXiv AI

Jul 14

AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP

arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.

By Aritra Mazumder, Nusrat jahan Lia

llms agents

Related stories

Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents

SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests

Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs

Evaluating Agentic Code Repair Capabilities in Distributed Systems

An Executable Benchmarking Suite for Tool-Using Agents

AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP