BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery

• URL: http://arxiv.org/abs/2606.30335v1
• Date: Mon, 29 Jun 2026 14:14:33 GMT
• Title: BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery
• Abstract summary: BayesEvolve is a belief-guided discovery framework that converts experimental evidence into a predictive belief state.<n>We show that BayesEvolve exhibits productive late-stage concentration rather than unfocused exploration.
• Score: 10.04049356690421
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous scientific discovery systems increasingly use large language models (LLMs) to propose new hypotheses, but many such systems condition primarily on experimental memory: archives of high-scoring candidates or heuristic summaries of recent trials. We argue that discovery agents should instead maintain explicit, uncertainty-aware beliefs about hypothesis quality. We introduce BayesEvolve, a belief-guided discovery framework that converts experimental evidence into a predictive belief state and uses this belief to guide future experimentation. As a controlled testbed for belief-guided discovery, we evaluate BayesEvolve on shifted BBOB-style black-box optimization tasks, leaving program and laboratory discovery domains to future work. BayesEvolve improves sample efficiency over memory- and archive-guided LLM baselines under a fixed evaluation budget. We further show that the belief state is predictive on held-out candidate pools, that controlled decision-rule ablations favor belief-guided selection with an annealed uncertainty bonus, and that BayesEvolve exhibits productive late-stage concentration rather than unfocused exploration.

Related papers

• EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation [68.80901568810616]
  EvoSCM aims to equip scientific agents with explicit structural causal models that evolve as new evidence is collected.<n>We evaluate EvoSCM onPhysics, a benchmark requiring agents to uncover the hidden dynamics of noncanonical physical worlds through experimentation.
  arXiv  Detail & Related papers  (2026-09-01T16:55:56Z)
• Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery [95.44432473367836]
  Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.<n>We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discnative, and testable hypothesis spaces from inconclusive evidence.<n>We introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets.
  arXiv  Detail & Related papers  (2026-07-17T08:56:43Z)
• BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation [20.375742002723765]
  Large language models (LLMs) are typically deployed in multi-turn conversations.<n>We ask how closely LLMs' belief updates match those of a rational Bayesian reasoner in multi-turn settings.<n>We introduce BayesBench, a suite of simulation environments that probe this across three progressively complex tasks.
  arXiv  Detail & Related papers  (2026-06-29T19:30:32Z)
• Evidence-Informed LLM Beliefs for Continual Scientific Discovery [66.36520571709482]
  We introduce two complementary changes to the original search procedure: belief-update filtering and diversity.<n>We find that embedding-based retrieval-augmented generation over prior discoveries best anticipates eventual posteriors, identifying 37.5% of static surprisals as spurious.<n>We then modify search to avoid these spurious rewards and prioritize hypotheses that remain surprising under non-stationary beliefs.
  arXiv  Detail & Related papers  (2026-06-28T04:06:12Z)
• FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights [63.32178443510396]
  We introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery of established findings.<n>Even the strongest agents achieve limited rediscovery success (50 F1), exhibit high variance across runs, and display recurring failure modes in experimental design, execution, and evidence-based reasoning.
  arXiv  Detail & Related papers  (2026-02-02T23:21:13Z)
• Open-ended Scientific Discovery via Bayesian Surprise [63.26412847240136]
  AutoDS is a method for open-ended scientific discovery that instead drives scientific exploration using Bayesian surprise.<n>We evaluate AutoDS in the setting of data-driven discovery across 21 real-world datasets spanning domains such as biology, economics, finance, and behavioral science.
  arXiv  Detail & Related papers  (2025-06-30T22:53:59Z)
• MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback [136.27567671480156]
  We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests.<n>We frame experiment-guided ranking as a sequential decision-making problem.<n>Our approach significantly outperforms pre-experiment baselines and strong ablations.
  arXiv  Detail & Related papers  (2025-05-23T13:24:50Z)
• Differentially private Bayesian tests [1.3127313002783776]
  We present a novel differentially private Bayesian hypotheses testing framework that arise naturally under a principled data generative mechanism. By focusing on differentially private Bayes factors based on widely used test statistics, we circumvent the need to model the complete data generative mechanism.
  arXiv  Detail & Related papers  (2024-01-27T21:07:11Z)
• Towards Futuristic Autonomous Experimentation--A Surprise-Reacting Sequential Experiment Policy [7.485913259227432]
  An autonomous experimentation platform in manufacturing is supposedly capable of conducting a sequential search for suitable manufacturing conditions by itself or for discovering new materials with minimal human intervention. The core of the intelligent control of such platforms is a policy to decide where to conduct the next experiment based on what has been done thus far. We discuss whether it is beneficial to trade off exploitation versus exploration by measuring the element and degree of surprise associated with the immediate past observation.
  arXiv  Detail & Related papers  (2021-12-01T16:14:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.