Papers
arxiv:2606.07412

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

Published on Jun 5
· Submitted by
taesiri
on Jun 8
Authors:
,
,
,
,
,
,
,

Abstract

Socratic-SWE enables self-evolving software engineering agents by leveraging historical solving traces to generate targeted repair tasks that improve agent performance through iterative refinement.

LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks. Existing synthetic data methods typically create tasks through fixed mutation or bug-injection procedures, making the resulting distributions largely independent of the agent's own weaknesses and training progress. We introduce Socratic-SWE, a closed-loop self-evolution framework that reuses the agent's historical solving traces as a source of training signal. Rather than treating traces only as evidence for reward computation, Socratic-SWE distills them into structured agent skills that summarize recurring failures and effective repair patterns. These skills then guide the generation of targeted repair tasks in real repositories. Candidate tasks are checked through execution-based validation and scored with a solver-gradient alignment reward, so that the retained tasks are both verifiable and useful for improving the Solver. The updated Solver produces new traces, enabling the task curriculum to adapt over successive rounds. Across SWE-bench Verified, SWE-bench Lite, SWE-bench Pro, and Terminal-Bench 2.0, Socratic-SWE consistently improves over self-evolving baselines under the same compute budget, reaching 50.40% on SWE-bench Verified after three iterations. These results suggest that solving traces can serve as a scalable substrate for self-evolving SWE agents.

Community

Paper submitter

Socratic-SWE is a self-evolution framework for coding agents that distills historical solving traces into structured skills, enabling the generation of targeted tasks to improve software engineering performance.

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.07412 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.07412 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.07412 in a Space README.md to link it from this page.

Collections including this paper 5