44 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…
Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes
Yuhao Tan, Zhibang Yang, Fangkai Yang +9
Large language models (LLMs) have made automated program repair (APR) increasingly practical for real-world bugs, but repairing directly from bug reports remains underconstrained.…
ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory
Yue Fang, Zhibang Yang, Fangkai Yang +5
ToolAtlas introduces a graph‑based, provider‑side memory that records tool capabilities, failure limits, and how tools can be combined, allowing LLM agents to query this memory and…
A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
Zhuofan Shi, Ming Ma, Zekun Yao +7
Open-Ended Deep Research (OEDR) pushes LLM agents beyond short-form QA toward long-horizon workflows that iteratively search, connect, and synthesize evidence into structured repor…
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Zhuofan Shi, Mingzhe Ma, Lu Wang +8
Deep search requires agents to answer complex questions through multi-step web search, browsing, evidence comparison, and synthesis. A central challenge is deciding how to search w…
RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
Kenan Li, Rongzhi Li, Linghao Zhang +17
Language model (LM) agents have driven substantial progress in automated software engineering (SWE), yet building and testing software repositories at scale remains a largely manua…