发表机构
UC San Diego; Johns Hopkins University（加州大学圣迭戈分校; 约翰斯·霍普金斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PrimeScientist通过将研究资源分配形式化为序贯决策问题，并采用自适应MCTS策略平衡探索与利用，在12个AI研究任务中以更少尝试提升10.3%平均奖励，实现资源高效利用。
AI 中文摘要
自主研究智能体旨在自动化科学工作流程，从提出想法到进行实验和分析结果。然而，当前的AI和研究智能体能够提出的研究方向数量超过了可用资源允许其追求的数量。此外，每次尝试都可能消耗大量资源，要求智能体重新考虑如何在后续研究中投入资源。因此，如何战略性地决定研究投入应成为自主研究智能体的核心能力。为此，我们引入了PrimeScientist，它在连续的研究尝试中共同决定研究方向和资源投入。具体来说，我们将这一战略性研究资源分配的挑战形式化为一个序贯决策问题，其中剩余资源应明确指导研究策略。我们首先引入一个可执行的计划树，该树在多次尝试中保留竞争性计划及其结果。基于这一表示，我们提出了一种基于自适应蒙特卡洛树搜索（MCTS）的分配策略，利用实验反馈和剩余资源来平衡探索与利用。在AI研究、系统和代码优化以及机器学习工程中的综合评估表明，战略性分配同时提高了研究质量和样本效率。在12个AI研究任务中，在相同资源预算下，PrimeScientist相比AutoResearch平均奖励提高了10.3%，研究尝试次数减少了50.6%。我们相信，将研究资源分配作为明确的优化目标，将确立资源有效利用作为自主智能体驱动大规模科学突破的核心研究能力。
英文摘要
Autonomous research agents aim to automate scientific workflows, from proposing ideas to conducting experiments and analyzing results. Yet current AI and research agents can propose more directions than available resources allow them to pursue. Moreover, each attempt could consume substantial resources, requiring agents to reconsider how to invest in subsequent research. Thus, deciding how to invest research effort strategically should be a defining capability of autonomous research agents. Accordingly, we introduce PrimeScientist, which jointly determines research direction and resource investment across successive research attempts. Specifically, we formulate this challenge of strategic research effort allocation as a sequential decision problem where remaining resources should explicitly guide the research policy. We first introduce an executable plan tree that preserves competing plans and their outcomes across attempts. Building on this representation, we propose an adaptive MCTS-based allocation policy that balances exploration and exploitation using experimental feedback and remaining resources. Comprehensive evaluations across AI research, systems and code optimization, and machine learning engineering show that strategic allocation improves research quality and sample efficiency together. Across 12 AI research tasks, PrimeScientist improves average reward by 10.3% with 50.6% fewer research attempts than AutoResearch under the same resource budget. We believe making research effort allocation an explicit optimization target establishes effective resource use as a core research capability for autonomous agents to drive scientific breakthroughs at scale.
Comments30 pages, 5 figures, 16 tables. Code and data: https://github.com/Henri-XYu02/PrimeScientist
