Swe Agents Long Context Rl

Train LLM-based agents for multi-turn SWE tasks via rejection fine-tuning and DAPO RL, scaling to 131k context length achieving 39% Pass@1.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 1af22783de

Frequently asked questions

npx get-skill add adu2021/swe-agents-long-context-rl