让智能体通过优化外部工作区来提升复杂任务表现
Workspace Optimization: How to Train Your Agent
- 用可执行的工作区替代权重，模拟训练过程
- 在ARC-AGI-3上得分提升至38.4%，减少31%动作消耗
- 适合研究多轮交互与非微调智能体的开发者
基于前沿语言模型的现代智能体通常无法调整自身权重。本文提出，真正可训练的是智能体的‘工作区’——一个其读写与测试的结构化外部载体。我们称之为工作区优化。该方法适用于需要多轮交互的复杂任务，当前沿模型具备强先验但无法单次求解时尤为有效。我们提出一种系统性工作区演化机制：以实体代替参数，以证据代替数据，以反例代替损失，以文本反馈代替梯度。我们在DreamTeam中实现该思想，这是一个用于ARC-AGI-3的多智能体框架，各角色协作构建可执行世界模型、规划、假设、探测、策略制定与失败路由。在官方评分协议下，对25个游戏的公共测试集进行两次独立运行平均，其得分从现有最优基线的36%提升至38.4%，同时每局游戏环境动作减少31%。
原文摘要 · Abstract (English)
Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured external substrate it reads, writes, and tests; we call its evolution workspace optimization. Workspace optimization targets hard multi-turn environments where a frontier model has strong priors but cannot solve the task in a single shot, so the agent must learn through interaction. We propose a principled way to evolve the workspace, mirroring the structure of weight-space training: artifacts in place of parameters, evidence in place of data, counterexamples in place of losses, and textual feedback in place of gradients. We instantiate the idea in DreamTeam, a multi-agent harness for ARC-AGI-3 whose roles build an executable world model, plan, hypothesize, probe, strategize, and route failures. On the current 25-game ARC-AGI-3 public set under the official scoring protocol and averaged over two independent runs, DreamTeam improves the SOTA protocol-matched agent's score from 36% to 38.4%, while using 31% fewer environment actions per game.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。