Recent Papers / arXiv:2606.07412

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

arXiv:2606.07412Submitted Jun 8, 20260 benchmark results

Authors pending

View PDF ↗arXiv page ↗Edit
Abstract

Closed-loop self-evolution distills solving traces into structured skills to generate targeted repair tasks; achieves 50.40% on SWE-bench Verified after three iterations.

Tasks
edit
• Agentic AI
Results

No benchmark results recorded yet.

submit

Benchmark results referencing this paper haven't been added to the registry yet. If you have a reproduction, submit it →

CodeSOTA extraction

Benchmark evidence

edit
  • Socratic-SWE: exact SWE-bench Verified score per iteration (abstract reports 50.40% after 3 rounds)
Add or update benchmark results
Logged-in editor · benchmark trail
Read next

Three places to go from here.

Index
All papers
All tracked papers in the registry, with benchmark result, model, and leaderboard linkage where available.
Replacement
Papers with Code is dead — alternatives
What replaced PWC for each use case: LLMs, OCR, speech, vision, robotics.
Top hub
Agentic AI
Every benchmark in Agentic AI.