CausalRepair: Bridging the Causality Gap in Large Language Model-Based Automated Program Repair via Dual-Slicing
Source
Linhao Wu, Yizhou Chen, Zhen Yang, Pengyu Xue, Dan Hao
Author
Linhao Wu, Yizhou Chen, Zhen Yang, Pengyu Xue, Dan Hao
Published
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
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.
Why it matters
context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → construction, not model choice, is what moves repair accuracy here, and the slicing strategy transfers to any 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 → that has to assemble a debugging context.
articleCoupling Planning with Episodic Memory in LLM Agents for Software Issue ResolutionJiahao Zhang, Yifan Zhang, Yu Huang
articleValidation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?Xiaonan Xu, Wenjing Wu
articleOnline Monitoring and Corrective Steering of Programming AgentsShuyang Liu, Saman Dehghan, Ji Young Kim, Jatin Ganhotra, Martin Hirzel, Reyhaneh Jabbarvand