发表机构
Amazon AGI（亚马逊AGI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对预算受限的智能体搜索场景，提出ExTS树搜索策略，结合三种机制优化树搜索，在多项任务上实现性能提升，还提供了问题结构差异的诊断方法。
AI 中文摘要
预算受限的智能体搜索出现于大型语言模型（LLM）智能体必须在有限评估预算下优化候选方案的场景，原因可能是验证成本高昂、生成过程需要多次模型调用，或两者兼有。在该场景中，标准蒙特卡洛树搜索（MCTS）的预算分配存在缺陷：在访问次数较少时探索奖励占主导，无前景的兄弟节点会在有前景的分支深化前被扩展，且分支扩展与节点质量无关。本文提出ExTS，一种将扩展本身视为信息价值决策的树搜索策略，它结合了三种机制：用于在窄分数分布下分离候选方案的判别式奖励塑形、根据父节点奖励历史估计创建新分支价值的随机虚拟子节点，以及仅当节点分数证明预算成本合理时才进行扩展的质量条件分支。在提示优化、代码生成、分子结构阐明和智能体工作流优化任务中，ExTS与特定任务的树搜索基准相比具有竞争力或实现了性能提升，采用单一固定配置时平均相对增益为+5.5%。本文还提出了试点运行诊断方法，用于表征预算受限的智能体搜索问题在结构上的差异，既有助于理解问题空间，也为自适应调整提供了实用指导。
英文摘要
Budget-constrained agentic search arises when an LLM agent must refine candidates under a small evaluation budget, because validation is expensive, generation requires multiple model calls, or both. In this regime, standard MCTS allocates budget poorly: exploration bonuses dominate at low visit counts, unpromising siblings are expanded before promising chains can deepen, and branching is independent of node quality. We introduce ExTS, a tree-search policy that treats expansion itself as a value-of-information decision. ExTS combines three mechanisms: discriminative reward shaping to separate candidates under narrow score distributions, a stochastic virtual child that estimates the value of creating a new branch from the parent's reward history, and quality-conditioned branching that expands only when a node's score justifies the budget cost. Across prompt optimization, code generation, molecular structure elucidation, and agentic workflow optimization, ExTS is competitive with or improves over task-specific tree-search baselines, with an average relative gain of +5.5% using a single fixed configuration. We further introduce pilot-run diagnostics that characterize what makes budget-constrained agentic search problems structurally different from one another, providing both understanding of the problem space and practical guidance for adaptation.
