CoEvo-RSI 论文提出模型与执行框架协同进化框架，缓解脑身不匹配问题
CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?
一篇研究智能体自我改进的论文，Qwen3.5-9B 用它这套框架跑赢了 DeepSeek-V4-Pro 和 GLM-5.3，做 agent 的可以看看思路。
arXiv 论文提出 CoEvo-RSI，一个递归自我改进（RSI）框架，通过元智能体基于共享进化档案和执行反馈，双向继承历史执行框架设计与模型 checkpoint 选择或合并。该方法仅用自身拒绝采样轨迹做 SFT，就让 Qwen3.5-9B 在多个垂直任务上与更大模型竞争。在 TraceElephant 多智能体失败归因上比 DeepSeek-V4-Pro 高 14.16 个百分点的 agent 准确率，在 HomeBench VM 智能家居指令遵循上比 GLM-5.3 高 4.90 个百分点的成功率。
CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?
Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities. We study the persistent yet often overlooked brain--body mismatch problem in this paradigm, where an evolving harness (body) demands behaviors its model (brain) has not learned or restricts capabilities it already possesses. We introduce CoEvo-RSI, a RSI framework that advances model--harness co-evolution through agent-driven, bidirectional historical inheritance. Drawing on a shared evolutionary archive and execution feedback, a meta-agent coordinates harness development from historical designs with model checkpoint selection or merging and subsequent adaptation under the selected harness, aligning inherited capabilities with evolving execution requirements to reduce brain--body mismatch. Using only supervised fine-tuning (SFT) on its own rejection-sampled trajectories, CoEvo-RSI makes Qwen3.5-9B competitive with larger models across diverse vertical applications, including multi-agent failure attribution, role-aware text-to-SQL, and smart-home instruction following. It surpasses DeepSeek-V4-Pro on TraceElephant (+14.16 agent accuracy) and GLM-5.3 on HomeBench VM (+4.90 success rate), underscoring the need for brain--body alignment and the potential of bidirectional historical inheritance to advance agent co-evolution.
- IT之家10-19 06:37原文