11 papers
Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code
Chunqiu Steven Xia, Courtney Miller
Agentic coding tools are increasingly used to make autonomous repository-level changes to real-world projects. Prior work has largely evaluated these contributions at the pre-merge…
SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery
Yuvraj Virk, Zack Edds, Chunqiu Steven Xia +1
Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems. However, they tend to converge onto a single high-level approach, t…
SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
Hwiwon Lee, Jiawei Liu, Dongjun Kim +4
Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC)…
Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?
Chunqiu Steven Xia, Zhe Wang, Yan Yang +2
Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world sof…
UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging
Cheryl Lee, Chunqiu Steven Xia, Longji Yang +4
Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understand…
Fuzz4All: Universal Fuzzing with Large Language Models
Chunqiu Steven Xia, Matteo Paltenghi, Jia Le Tian +2
Fuzzing has achieved tremendous success in discovering bugs and vulnerabilities in various software systems. Systems under test (SUTs) that take in programming or formal language a…