让科研探索自动判断证据强度，避免过度推断。
StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery
- 用外部状态追踪探索进展，协调下一步研究方向
- 在40个真实数据任务中，生成更多高价值且有据可依的发现
- 适合需要持续迭代、避免冒进的开放性科研场景
开放性科学发现要求智能体超越预设问题的分析执行。在多轮探索中，发现智能体需判断哪些现象值得深入研究，同时避免过度解读——即提出的主张超出分析所支持的证据范围。这带来一个证据校准难题：探索路径必须与主张状态绑定，使证据同时指导后续探究和主张成立与否。我们提出StatefulDiscovery框架，将调查状态外化，并利用其协调前沿选择、证据获取与主张裁定。在40个真实数据发现任务上评估，相比多个基线方法，StatefulDiscovery生成的主张整体更受认可，既具备充分支持又具高价值。消融实验表明，结构化假设、局部裁定和前沿控制是性能提升的关键。结果表明，显式发现状态能有效耦合探索与证据校准的主张形成。
原文摘要 · Abstract (English)
Open-ended scientific discovery asks agents to move beyond executing analyses for predefined questions. Across multiple rounds of exploration, a discovery agent must decide which phenomena warrant investigation while avoiding overinterpretation, where emerging claims exceed the evidential scope of the analyses supporting them. This creates an evidence-calibration problem: the exploration trajectory must be coupled with claim status so that evidence can guide both what to investigate next and what can be claimed. We introduce StatefulDiscovery, a discovery framework that externalizes investigation state and uses it to coordinate frontier selection, evidence acquisition, and claim adjudication. We evaluate StatefulDiscovery across 40 real-data discovery tasks. Compared with several baselines, StatefulDiscovery produces more claims overall judged to be both well-supported and high-value. Ablations indicate that structured hypotheses, local adjudication, and frontier control contribute to performance. Together, these results suggest that explicit discovery state can couple exploration with evidence-calibrated claim formation.
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。