Counterexamples as Feedback for Agent Self-Correction
Source
Sidhesh Badrinarayan, Adithya Parthasarathy
Author
Sidhesh Badrinarayan, Adithya Parthasarathy
Date
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.
Why it matters
How you phrase repair feedback to a coding 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 → matters enormously: concrete counterexamples that show exactly where an artifact fails beat generic 'try again' or error-only feedback by a wide margin in multi-turn self-correction.
articleGrounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test GenerationMichele Tufano, James McClure, Jos\'e Cambronero, Runxiang Cheng, Sherry Y. Shi, Renyao Wei, Dorothy Chen, Franjo Ivan\v{c}i\'c, Livio Dalloro, Pat Rondon
articleTIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code GenerationMinyu Chen, Sihao Wu, Ling-I Wu, Song Qin, Jingyang Li, Lei Ning, Jianxin Xue, Guoqiang Li
articleAuditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle ProblemYunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni