6 papers
A Comprehensive Study of Implementation Bugs in Multi-modal Agents
Suwan Li, Lei Bu, Shangqing Liu +5
Multi-Modal Agents (M-agents), empowered by Large Language Models (LLMs), excel in various complex, open-world scenarios such as autonomous driving and robotics. However, their uni…
Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents
Wei Ma, Zhi Chen, Jingxu Gu +3
Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution rates: that a test step follows…
SpecSyn: LLM-based Synthesis and Refinement of Formal Specifications for Real-world Program Verification
Lezhi Ma, Shangqing Liu, Yi Li +3
Program verification is a formal technique to rigorously ensure the correctness and fault-freeness of software systems. However, constructing comprehensive interprocedural specific…
Defects4C: Benchmarking Large Language Model Repair Capability with C/C++ Bugs
Jian Wang, Xiaofei Xie, Qiang Hu +4
Automated Program Repair (APR) plays a critical role in enhancing the quality and reliability of software systems. While substantial progress has been made in Java-based APR, large…
Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models
Jian Wang, Xiaofei Xie, Qiang Hu +2
Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their…
Intention is All You Need: Refining Your Code from Your Intention
Qi Guo, Xiaofei Xie, Shangqing Liu +3
Code refinement aims to enhance existing code by addressing issues, refactoring, and optimizing to improve quality and meet specific requirements. As software projects scale in siz…