5-4B and the SWE-agent tool-use framework.
Training on failed patches helps coding agents recover more effectively
FC-SWE teaches repository-level coding agents to use failed patches and verifier diagnostics in subsequent attempts.
Big Tech
Jia Liufu · Bin Hu · Linglin Jing · Terry Kong · Yuki Huang · Ashwath Aithal · +2 more
NVIDIA · Tsinghua University
Research Digest··3 min read
Liufu et al.
Why this paper
From NVIDIA and Tsinghua University
In one line
Training software engineering agents on recovery attempts conditioned on failed patches and verifier feedback improves resolution rates over standard GRPO.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§