Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly Discrepancies
Source
arxiv.org
Author
Liyan Huang, Kaicheng Wang, Weihang Wang
Date
Why it matters
Localizing where execution first diverges before invoking the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → lifted the repair rate from 50.2% to 70.0% — evidence that narrowing an agent's search space beats handing it more tools or instrumentation.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
articleEvaluating Agentic Code Repair Capabilities in Distributed SystemsYibo Yan, Huijuan Wang, Junzhou He, Yizhuo Liang, Shaoyu Wang, Huanchen Sun, Seo Jin Park
articleCausalRepair: Bridging the Causality Gap in Large Language Model-Based Automated Program Repair via Dual-SlicingLinhao Wu, Yizhou Chen, Zhen Yang, Pengyu Xue, Dan Hao
articleCoupling Planning with Episodic Memory in LLM Agents for Software Issue ResolutionJiahao Zhang, Yifan Zhang, Yu Huang