StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery

Computer Science > Artificial Intelligence [Submitted on 10 Jun 2026] StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery Jiayao Chen, Shi Liu, Linyi Yang 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. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.11851 [cs.AI]   (or arXiv:2606.11851v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.11851 Focus to learn more Submission history From: Jiayao Chen [view email] [v1] Wed, 10 Jun 2026 09:28:28 UTC (2,709 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)