fault-localization

Tag

Cards List
#fault-localization

PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

arXiv cs.AI · 2026-07-22 Cached

PhoenixRepair is a multi-agent framework that systematically explores multiple candidate edit locations and performs iterative reflection and refinement on patch generation, achieving state-of-the-art results on SWE-bench-Verified with a 76.0% Pass@1 rate under MiniMax-M2.5 and a 7.8% relative improvement over SWE-agent under DeepSeek-V3.1.

0 favorites 0 likes
#fault-localization

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

Hugging Face Daily Papers · 2026-04-19 Cached

This paper introduces the Precise Debugging Benchmark (PDB), a framework that evaluates LLMs on precise fault localization rather than just test pass rates. Results show frontier models like GPT-4.1-Codex and DeepSeek-V3.2-Thinking pass 76%+ of unit tests but achieve less than 45% edit precision, revealing a critical gap between code regeneration and true debugging.

0 favorites 0 likes
← Back to home

Submit Feedback