Strategist：用元智能体自动进化推理策略
Strategist: Evolving Reasoning with Agents
一篇把推理策略交给智能体自己进化的论文，30 个基准里赢了 24 个，成本还降 39%，做 Agent 的人可以看看思路。
论文提出 Strategist，一个能在不同任务间进化推理策略的元智能体。每条策略以 blueprint 形式写成可执行代码，供后续策略复用，形成策略库。Strategist 依据任务和少量开发集样本检索相关 blueprint、生成候选策略、在真实样本上测试并据结果修订。在 30 个基准上，Strategist 在 24 个基准超过最强基线，平均准确率 74.7% 对比 74.0%，推理成本低 39%。
Strategist: Evolving Reasoning with Agents
A model is only half of an AI agent system. The other half is the inference strategy: the reasoning procedure that turns model calls into a response. Today that second half is written by hand, and the experience of building one strategy never carries to the next. We introduce Strategist, a meta-agent that evolves inference strategies across tasks. Each strategy is written as a blueprint,executable code that other strategies can reuse, and together the blueprints form a library. Given a task and a small development set, Strategist retrieves related blueprints, writes candidate strategies, tests them on real samples, and revises them from the results. Every candidate then enters the library, so later tasks build on earlier discoveries. On 30 benchmarks, Strategist beats the strongest baseline on 24 and matches its average accuracy (74.7% vs.74.0%) at 39% lower inference cost. Its strategies also transfer to unseen tasks and other models without further search. The part of an AI system that is not improved on its own now does.