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

arXiv: https://arxiv.org/abs/2606.11851 · HTML: https://mlsanity.com/paper/2606.11851/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 30 of 32)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026)
- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology](https://mlsanity.com/paper/2503.00096/) (2025)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [BLADE: Benchmarking Language Model Agents for Data-Driven Science](https://mlsanity.com/paper/2408.09667/) (2024)
- [StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows](https://mlsanity.com/paper/2403.11322/) (2024)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [Explaining Length Bias in LLM-Based Preference Evaluations](https://mlsanity.com/paper/2407.01085/) (2024)
- [SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources](https://mlsanity.com/paper/2604.03964/) (2026)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration](https://mlsanity.com/paper/2505.15047/) (2025)
- [PACEvolve: Enabling Progress-Aware Consistent Evolution](https://mlsanity.com/paper/2601.10657/) (2026)
- [AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery](https://mlsanity.com/paper/2604.05550/) (2026)
- [Accelerating Scientific Discovery with Autonomous Goal-evolving Agents](https://mlsanity.com/paper/2512.21782/) (2025)
- [Empowering Scientific Workflows with Federated Agents](https://mlsanity.com/paper/2505.05428/) (2025)
- [HeurekaBench: A Benchmarking Framework for AI Co-scientist](https://mlsanity.com/paper/2601.01678/) (2026)
- [Belief Memory: Agent Memory Under Partial Observability](https://mlsanity.com/paper/2605.05583/) (2026)
- [CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges](https://mlsanity.com/paper/2603.11863/) (2026)
- [Principle-Evolvable Scientific Discovery via Uncertainty Minimization](https://mlsanity.com/paper/2602.06448/) (2026)
- [From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents](https://mlsanity.com/paper/2602.13855/) (2026)
- [Mozi: Governed Autonomy for Drug Discovery LLM Agents](https://mlsanity.com/paper/2603.03655/) (2026)

## Built on by (most cited first, 1 of 1)

- [Socratic agents for autonomous scientific discovery in high-dimensional physical systems](https://mlsanity.com/paper/2606.26722/) (2026)

## Abstract (arXiv)

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. 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 textscStatefulDiscovery, a discovery framework that externalizes investigation state and uses it to coordinate frontier selection, evidence acquisition, and claim adjudication. We evaluate textscStatefulDiscovery across 40 real-data discovery tasks. Compared with several baselines, textscStatefulDiscovery produces more claims overall judged to be both well-supported and high-value. Ablations indicate distinct roles for structured hypotheses, local adjudication, frontier control and persistent states. Together, these results suggest that explicit discovery state can couple exploration with evidence-calibrated claim formation. Our code is released at hrefhttps://github.com/SUSTech-GenAI/StatefulDiscovery.githttps://github.com/SUSTech-GenAI/StatefulDiscovery.git.