12 papers
LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation
Han Li, Zhemin Fang, Rili Feng +8
Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing ben…
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
Xiangxin Zhao, Han Li, Shuaiting Li +4
Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a gro…
KAT-Coder-V2.5 Technical Report
Bo Huang, Fengxiang Li, Hao Xu +50
We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capabili…
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Zhanbo Hua, Yifan Yao, Weihao Xie +14
While recent LLM-based terminal agents have demonstrated promising capabilities, the scarcity of high-quality, executable training data remains a critical bottleneck. Existing synt…
EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems
Shuang Xie, Yunan Lu, Han Li +1
In large-scale enterprise settings, centralized multi-agent systems (MAS) are increasingly adopted, in which a coordinator delegates user requests to lightweight, domain-specialize…
ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents
Chinmay Savadikar, Mingyu Zhao, Yuanzheng Zhu +5
Developing and evaluating e-commerce web agents requires environments that preserve meaningful task structure while enabling controllable, reproducible, and scalable scientific com…