Saved in:
Bibliographic Details
Main Authors: Meng, Qianru, Zhang, Xiao, Ren, Zhaochun, Visser, Joost
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.27238
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • LLM-based agents have moved automated program repair (APR) from fixed-context patch generation to interactive repository-level repair. However, existing agentic APR systems still struggle to use execution evidence to guide localization, patch generation, and validation. We propose EviACT (Evidence-to-Action), an agentic APR framework that coordinates three evidence-driven guardrails across repair stages. The retrieval scaffold grounds repair context, the compile gate filters invalid edits, and the test-driven gate checks target-test recovery before full regression. Across four benchmarks, EviACT improves resolve rate over the strongest reported comparable baselines by 1.6-6.0 percentage points and shows 70.1-88.6% lower reported per-bug API cost where baseline costs are available. Ablations and diagnostics suggest that these gains are associated with the coordinated evidence-to-action chain, making agentic APR more effective and efficient.