微软这新研究，用简单方式让开源大模型代码能力提升，和之前比进步明显，值得看看。
微软的新研究借助Agent Lightning v1.0框架，使开源大模型Qwen3.5 - 9B在代码推理基准SWE - bench上的通过率从41.8%提升至56.4%；该研究仅用约3500行代码实现模型与强化学习连接，优化训练流程；通过6K条训练示例和适度计算资源，模型在该基准表现提升14.6个百分点。
Very interesting new work from Microsoft. (bookmark it) This work is related to this emerging them...
Very interesting new work from Microsoft. (bookmark it) This work is related to this emerging theme of leveraging harnesses for model post-training. Modern agents run inside a harness that owns tools, context, and control flow. When you train them, the harness owns the environment loop and the trainer only sees LLM request and response pairs. How it works. Agent Lightning v1.0 connects any harness to RL through an endpoint proxy in about 3,500 lines, then works through what breaks in that setup, retokenization, sample merging, advantage calculation, loss normalization, and backend scheduling. Using 6K training examples and modest compute, it moves Qwen3.5-9B on SWE-bench Verified from 41.8% to 56.4%. Paper: arxiv.org/abs/2608.17528 Track more trending AI papers in our academy: academy.dair.ai 💬 13 🔄 41 ❤️ 208 👀 12559 📊 78 ⚡
- Decoder08-18 08:22原文