7 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…
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
Haomin Qi, Xingliang Wang, Xuanqi Gao +9
The paper introduces Change2Task, a system that turns merged pull requests from software repositories into verified, executable coding‑agent tasks by reconstructing the code state…
Towards a Systems Foundation for Agentic Cloud Management
Minghao Li, Ziqian Liu, Ziyu Mao +5
The paper proposes CloudWeaver, a systems layer that lets autonomous agents safely manage cloud resources by providing scoped views and coordinating concurrent operations, ensuring…
Can Large Language Models Generate Observability-Aware Code?
Yongliang Tao, Hongyu Zhang, Pengfei Gao +8
Recent advances in coding agents have enabled the generation of increasingly complex software systems. While existing evaluations primarily focus on functional correctness, product…
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
Kaikai An, Fangkai Yang, Liqun Li +10
Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid '5Ws' questions. However, significant chall…
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
Shangding Gu, Bilgehan Sel, Yuhao Ding +4
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during e…