12 papers
Self-Evolving Coding Agents
Hao Zhou, Haichuan Hu, Ye Shang +1
Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and g…
MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs
Haichuan Hu, Chunrong Fang, Ye Shang +5
The paper introduces MultiFixer, a multi-agent framework that uses a Coordinator‑Proposer architecture to coordinate large language model generated patches for fixing bugs that spa…
ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports
Quanjun Zhang, Yi Zheng, Ye Shang +5
Reproduction tests help developers confirm reported issues and provide executable feedback for issue resolution, yet issue reports in open-source projects rarely include such tests…
Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows
Quanjun Zhang, Ye Shang, Siqi Gu +4
Recently, the emergence of Large Language Models (LLMs) has spurred a surge of research into automated unit test generation, yielding impressive performance and reducing manual eff…
PSearch: Search-based Patch Generation in the Era of LLM-based Automated Program Repair
Haichuan Hu, Ye Shang, Weifeng Sun +1
Large Language Models (LLMs) have substantially advanced Automated Program Repair (APR), yet most existing LLM-based APR methods still rely on trial-and-error to generate patches.…
Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution
Ye Shang, Quanjun Zhang, Haichuan Hu +3
As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, by…