3 papers
cs.SE2026
Trustworthy Software Project Generation : a Case Study with an Interactive Theorem Prover
Jian Fang, Yingfei Xiong
Generating code from natural-language requirements has become a primary route for LLM-assisted software development. Although LLMs can successfully complete small programming tasks…
cs.SE2026
Reducing Cost of LLM Agents with Trajectory Reduction
Yuan-An Xiao, Pengfei Gao, Chao Peng +1
Multi-turn agent systems based on Large Language Models (LLMs) have become increasingly popular for software engineering tasks. While LLM agents demonstrate promising effectiveness…
cs.SE2025
PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates
Yuan-An Xiao, Weixuan Wang, Dong Liu +3
Fixing static analysis alerts in source code with Large Language Models (LLMs) is becoming increasingly popular. However, LLMs often hallucinate and perform poorly for complex and…