Microsoft 论文 ScholarEvolve：从已发表研究中自动演化 Agent 框架
New paper from Microsoft and colleagues on evolving agent harnesses. It's a really cool idea to evo...
Microsoft 这篇 ScholarEvolve 不改模型、只改 harness，就让 Qwen3.5-27B 在 AppWorld 上涨了 14 个点，思路很新颖。
Microsoft 团队发布论文 ScholarEvolve，思路是用已发表的 Agent 研究论文来改进 harness，而不是分析 Agent 自身的失败日志。它把 harness 拆成工具使用、记忆管理、任务执行三个模块，对近期论文做主题建模，为每个模块提取改进策略，再组合实现并测试。在模型固定不变的情况下，Qwen3.5-27B 在 AppWorld Challenge 的任务完成率从 49.6% 提升到 63.6%，GPT-5.4-mini 在 Tau2-Bench Telecom 从 72.7% 提升到 81.9%。新论文可以持续加入，让 harness 随研究进展不断演化。
New paper from Microsoft and colleagues on evolving agent harnesses. It's a really cool idea to evo...
New paper from Microsoft and colleagues on evolving agent harnesses. It's a really cool idea to evolve a harness from published research. Something I have also been testing for the past couple of months. ScholarEvolve proposes harness changes based on published agent research rather than the agent's own failure logs. It splits the harness into modules for tool use, memory management, and task execution. It runs topic modeling over recent papers to identify distinct improvement strategies for each module, then implements and tests combinations. New papers can be added over time. With the model held fixed, Qwen3.5-27B goal completion on AppWorld Challenge rises from 49.6% to 63.6%, and GPT-5.4-mini on Tau2-Bench Telecom rises from 72.7% to 81.9%. Paper: arxiv.org/abs/2609.40169 Chat with Paper: academy.dair.ai/papers/learnin… 💬 5 🔄 9 ❤️ 18 👀 2076 📊 10 ⚡
