paper
Probe-and-Refine Tuning of Repository Guidance for Coding Agents
paperactiveprovisional
probe-and-refine-tuning-of-repository-guidance-for-coding-agents-f4d37ea4·1 events·first seen 2d agoAliases: Probe-and-Refine Tuning of Repository Guidance for Coding Agents
Co-occurring entities
More like this (12)
Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedbackverification-refinement loopBenchmark AgentChain-of-Thought Fine-TuningGitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and MergePrompt TuningAgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibilitysupervised fine-tuningtool-calling agentsPivotal TuningCognizant Agent Foundryinstruction tuning
Recent events (1)
Probe-and-Refine Tuning improves coding agent performance via iterative repository guidance refinement
A new arXiv paper introduces probe-and-refine tuning, a procedure that uses synthetic bug-fix probes to iteratively improve AGENTS.md repository guidance files for LLM-based coding agents without requiring an agent loop during tuning. Evaluated on SWE-bench Verified with Qwen3.5-35B-A3B, the method achieves 33.0% mean resolve rate versus 28.3% for a static knowledge base baseline and 25.5% for an unguided baseline. The improvement is attributed to coverage gains—refined guidance helps agents locate the correct files rather than improving patch quality—and a step-budget experiment shows guidance is necessary for agents to productively use larger compute budgets.