@HuggingPapers: Recursive Self-Rewrite scales model capability on complex tasks A single base model (Qwen-3.8-27B) discovers solutions …

X AI KOLs Following Papers
self-improvement reinforcement-learning agentic-tasks qwen benchmark training-data open-source

Summary

HuggingPapers 介绍了一篇关于 Recursive Self-Rewrite 的研究：单一基础模型 Qwen-3.8-27B 在多种 harness 下发现解法并将其改写为可复用的训练轨迹，使 Terminal-Bench 2 的 Pass@3 从 57.0% 提升到 74.2%。

Recursive Self-Rewrite scales model capability on complex tasks A single base model (Qwen-3.8-27B) discovers solutions across diverse harnesses, then rewrites them into reusable training trajectories under a general harness. Pass@3 on Terminal-Bench 2 jumps from 57.0% to 74.2%. https://t.co/lbtTF5P6YC
Original Article
View Cached Full Text

Cached at: 10/06/26, 03:49 PM

Recursive Self-Rewrite scales model capability on complex tasks

A single base model (Qwen-3.8-27B) discovers solutions across diverse harnesses, then rewrites them into reusable training trajectories under a general harness. Pass@3 on Terminal-Bench 2 jumps from 57.0% to 74.2%. https://t.co/lbtTF5P6YC

Similar Articles

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Hugging Face Daily Papers

The paper proposes Recursive Self-Rewrite (RSR), a framework where a single base model (Qwen-3.8-27B) discovers successful solutions under diverse harnesses and reconstructs them into training trajectories under a general harness via a planner-critic-executor loop, yielding significant pass@3 gains on terminal-bench tasks after supervised finetuning.

Self-Supervised Scaling of Terminal Environments for Scientific Domains

Hugging Face Daily Papers

提出软件在环重构（software-in-the-loop reconstruction）的自监督框架，从现有科学软件工作流中自动生成可执行参考行为与验证目标，用于训练终端智能体；使用 Qwen3.8-Max 生成训练数据并对 Qwen3.8-27B 微调，使 Terminal-Bench2 平均性能从 47.94% 提升至 53.56%。