9 papers
SWE-chat: Coding Agent Interactions From Real Users in the Wild
Joachim Baumann, Vishakh Padmakumar, Xiang Li +3
AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We present SWE-chat,…
Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
Fazhong Liu, Zhuoyan Chen, Tu Lan +6
Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and…
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Songcheng Cai, Zhiheng Lyu, Yuansheng Ni +13
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often over…
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
Pei Yang, Wanyi Chen, Asuka Yuxi Zheng +11
Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three c…
HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid
Xiang Li, Siyu Lu, Federica Sarro +2
Automated software environment setup is a prerequisite for testing, debugging, and reproducing failures, yet remains challenging in practice due to complex dependencies, heterogene…
Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
Xiang Li, Zhiwei Fei, Ying Ma +3
Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabi…