Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
Ranking
Observed public metrics from 1 member.
Merged summary
TL;DR - Model Discovery Agent (MDA) pairs an LLM proposing candidate mechanistic model structures with Bayesian inference and value-of-information experiment design, aiming to learn causal world models from very few interventions. It matters because interventional "what if" prediction needs mechanism, not curve fitting, and experiments are expensive.
- Architecture: LLM acts as a structure proposer; sequential Monte Carlo handles parameter/structure posteriors, simulation-based inference covers intractable likelihoods, and VoI selects the next experiment.
- Operates in the M-open setting: a predictive check flags when truth lies outside the current hypothesis class, triggering the proposer to expand the hypothesis space, with new parameters identified by designed experiments.
- Core claim is a discovery–design feedback loop: designed experiments identify proposed mechanisms, better-identified mechanisms improve predictions, and remaining unexplained residuals drive further discovery.
- Evaluated on three benchmarks spanning physics, chemistry, and a new partially observed single-neuron electrophysiology benchmark (HH); authors report SOTA in data-efficient model learning and interventional forecasting.
Sources (1)
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
TL;DR - Model Discovery Agent (MDA) pairs an LLM proposing candidate mechanistic model structures with Bayesian inference and value-of-information experiment design, aiming to learn causal world models from very few interventions. It matters because interventional "what if" prediction needs mechanism, not curve fitting, and experiments are expensive.
- Architecture: LLM acts as a structure proposer; sequential Monte Carlo handles parameter/structure posteriors, simulation-based inference covers intractable likelihoods, and VoI selects the next experiment.
- Operates in the M-open setting: a predictive check flags when truth lies outside the current hypothesis class, triggering the proposer to expand the hypothesis space, with new parameters identified by designed experiments.
- Core claim is a discovery–design feedback loop: designed experiments identify proposed mechanisms, better-identified mechanisms improve predictions, and remaining unexplained residuals drive further discovery.
- Evaluated on three benchmarks spanning physics, chemistry, and a new partially observed single-neuron electrophysiology benchmark (HH); authors report SOTA in data-efficient model learning and interventional forecasting.