# Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models

arXiv: https://arxiv.org/abs/2608.09696 · HTML: https://mlsanity.com/paper/2608.09696/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 41 of its 110 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 41)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Causal Consistency of Structural Equation Models](https://mlsanity.com/paper/1707.00819/) (2017)
- [Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design](https://mlsanity.com/paper/2103.02438/) (2021)
- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [Elements of Sequential Monte Carlo](https://mlsanity.com/paper/1903.04797/) (2019)
- [Prediction-Oriented Bayesian Active Learning](https://mlsanity.com/paper/2304.08151/) (2023)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl](https://mlsanity.com/paper/2305.01582/) (2023)
- [Integrating Large Language Model for Improved Causal Discovery](https://mlsanity.com/paper/2306.16902/) (2023)
- [Combining Induction and Transduction for Abstract Reasoning](https://mlsanity.com/paper/2411.02272/) (2024)
- [Optimal experimental design: Formulations and computations](https://mlsanity.com/paper/2407.16212/) (2024)
- [Automated Hypothesis Validation with Agentic Sequential Falsifications](https://mlsanity.com/paper/2502.09858/) (2025)
- [Evaluating Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2512.15567/) (2025)
- [Automated Statistical Model Discovery with Language Models](https://mlsanity.com/paper/2402.17879/) (2024)
- [ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence](https://mlsanity.com/paper/2603.24621/) (2026)
- [NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents](https://mlsanity.com/paper/2510.07172/) (2025)
- [Simulation-Based Inference: A Practical Guide](https://mlsanity.com/paper/2508.12939/) (2025)
- [BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design](https://mlsanity.com/paper/2508.21184/) (2025)
- [The Statistical Accuracy of Neural Posterior and Likelihood Estimation](https://mlsanity.com/paper/2411.12068/) (2024)
- [BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery](https://mlsanity.com/paper/2501.01540/) (2025)
- [Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery](https://mlsanity.com/paper/2502.15224/) (2025)
- [Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab](https://mlsanity.com/paper/2507.02083/) (2025)
- [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)
- [Likelihood-free MCMC with Amortized Approximate Ratio Estimators](https://mlsanity.com/paper/1903.04057/) (2019)
- [DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking](https://mlsanity.com/paper/2605.26087/) (2026)
- [Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery](https://mlsanity.com/paper/2605.08956/) (2026)
- [Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist](https://mlsanity.com/paper/2606.26448/) (2026)

## Built on by (most cited first, 7 of 7)

- [Recursive self-improvement of AI research agents](https://mlsanity.com/paper/2609.26457/) (2026)
- [When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models](https://mlsanity.com/paper/2608.26187/) (2026)
- [EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights](https://mlsanity.com/paper/2610.00492/) (2026)
- [ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe](https://mlsanity.com/paper/2610.03092/) (2026)
- [When Should an In-Context Learner Expand Its Hypothesis Space?](https://mlsanity.com/paper/2610.09471/) (2026)
- [Kernel Autoresearch for Open-Ended Model Discovery](https://mlsanity.com/paper/2610.10394/) (2026)
- [LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models](https://mlsanity.com/paper/2610.11253/) (2026)

## Abstract (arXiv)

A primary goal of science is to learn mechanistic world models from limited experimental data, both to explain observations and to predict novel interventions. We introduce the Model Discovery Agent (MDA), which combines LLM proposals for mathcal M-open model discovery, experiment design based on Value of Information, and approximate Bayesian inference over model structures, parameters, and stochastic latent trajectories. We apply MDA to learn symbolic reaction rate laws for ChemBench citepkabra2026autoscilab, partially observed ODE models for GlucoseBench citepxie2018simglucose,kovatchev2009insilico, and partially observed SDE models for a new stochastic single-neuron simulator we create. In the appendix, we also show results on various other domains from BoxingGym citepgandhi2025boxinggym. We show that MDA has improved sample efficiency compared to various baseline methods, and the learned models are good predictors but also provide interpretable abstractions of each domain.