# AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

arXiv: https://arxiv.org/abs/2507.00310 · HTML: https://mlsanity.com/paper/2507.00310/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 19 of 19)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [BLADE: Benchmarking Language Model Agents for Data-Driven Science](https://mlsanity.com/paper/2408.09667/) (2024)
- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [OMNI: Open-endedness via Models of human Notions of Interestingness](https://mlsanity.com/paper/2306.01711/) (2023)
- [CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation](https://mlsanity.com/paper/2503.22708/) (2025)
- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [AutoBencher: Towards Declarative Benchmark Construction](https://mlsanity.com/paper/2407.08351/) (2024)
- [Automated Hypothesis Validation with Agentic Sequential Falsifications](https://mlsanity.com/paper/2502.09858/) (2025)
- [HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation](https://mlsanity.com/paper/2504.11524/) (2025)
- [Data-driven Discovery with Large Generative Models](https://mlsanity.com/paper/2402.13610/) (2024)
- [MacroBase: Prioritizing Attention in Fast Data](https://mlsanity.com/paper/1603.00567/) (2016)

## Built on by (most cited first, 30 of 33)

- [Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents](https://mlsanity.com/paper/2602.16699/) (2026)
- [A Probabilistic Framework for LLM-Based Model Discovery](https://mlsanity.com/paper/2602.18266/) (2026)
- [LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs](https://mlsanity.com/paper/2605.24043/) (2026)
- [MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time](https://mlsanity.com/paper/2508.08641/) (2025)
- [CREATE: Testing LLMs for Associative Creativity](https://mlsanity.com/paper/2603.09970/) (2026)
- [Unlocking LLM Creativity in Science through Analogical Reasoning](https://mlsanity.com/paper/2605.11258/) (2026)
- [auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation](https://mlsanity.com/paper/2606.26460/) (2026)
- [Generating Literature-Driven Scientific Theories at Scale](https://mlsanity.com/paper/2601.16282/) (2026)
- [Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence](https://mlsanity.com/paper/2606.01444/) (2026)
- [Accelerating Social Science Research via Agentic Hypothesization and Experimentation](https://mlsanity.com/paper/2602.07983/) (2026)
- [Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents](https://mlsanity.com/paper/2607.09195/) (2026)
- [Autonomous Scientific Discovery via Iterative Meta-Reflection](https://mlsanity.com/paper/2607.01131/) (2026)
- [Accelerating Scientific Research with Gemini in the Real-World](https://mlsanity.com/paper/2608.26701/) (2026)
- [Agentic Discovery with Active Hypothesis Exploration for Visual Recognition](https://mlsanity.com/paper/2604.12999/) (2026)
- [InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis](https://mlsanity.com/paper/2604.13201/) (2026)
- [Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis](https://mlsanity.com/paper/2604.23072/) (2026)
- [StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery](https://mlsanity.com/paper/2606.11851/) (2026)
- [Evidence-Informed LLM Beliefs for Continual Scientific Discovery](https://mlsanity.com/paper/2606.29182/) (2026)
- [Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model](https://mlsanity.com/paper/2607.20058/) (2026)
- [Hypothesis-Driven Deep Research with Large Language Models: A Structured Methodology for Automated Knowledge Discovery](https://mlsanity.com/paper/2605.10224/) (2026)
- [Epistemic Uncertainty for Test-Time Discovery](https://mlsanity.com/paper/2605.11328/) (2026)
- [Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent](https://mlsanity.com/paper/2606.01816/) (2026)
- [Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery](https://mlsanity.com/paper/2606.02632/) (2026)
- [EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation](https://mlsanity.com/paper/2607.01584/) (2026)
- [Baikal: Structured Search for Deep Research over Data Lakes](https://mlsanity.com/paper/2607.27726/) (2026)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)
- [Bioinfoysis Technical Report](https://mlsanity.com/paper/2609.03871/) (2026)
- [BOReFT: Manifold Steering of Language Models for Black-box Optimization](https://mlsanity.com/paper/2609.33722/) (2026)
- [QuantForge: Discovering Residual Decompositions for MXFP4 Post-Training Quantization](https://mlsanity.com/paper/2609.34680/) (2026)
- [Reinforcing Agentic Creativity in Scientific Ideation with Night Science](https://mlsanity.com/paper/2609.35706/) (2026)

## Abstract (arXiv)

The promise of autonomous scientific discovery (ASD) hinges not only on answering questions, but also on knowing which questions to ask. Most recent works in ASD explore the use of large language models (LLMs) in goal-driven settings, relying on human-specified research questions to guide hypothesis generation. However, scientific discovery may be accelerated further by allowing the AI system to drive exploration by its own criteria. The few existing approaches in open-ended ASD select hypotheses based on diversity heuristics or subjective proxies for human interestingness, but the former struggles to meaningfully navigate the typically vast hypothesis space, and the latter suffers from imprecise definitions. This paper presents AutoDiscovery -- a method for open-ended ASD that instead drives scientific exploration using Bayesian surprise. Here, we quantify the epistemic shift from the LLM's prior beliefs about a hypothesis to its posterior beliefs after gathering experimental results. To efficiently explore the space of nested hypotheses, our method employs a Monte Carlo tree search (MCTS) strategy with progressive widening using surprisal as the reward function. We evaluate AutoDiscovery in the setting of data-driven discovery across 21 real-world datasets spanning domains such as biology, economics, finance, and behavioral science. Our results demonstrate that under a fixed budget, AutoDiscovery substantially outperforms competitors by producing 5-29% more discoveries deemed surprising by the LLM. Our human evaluation further reveals that two-thirds of discoveries made by our system are surprising to domain experts as well, suggesting this is an important step towards building open-ended ASD systems.