LLM + RL Agent Achieves New SOTA in Scientific Discovery, Introduces NeuronBench

sirbayes · x · 2026-08-12

The author introduces an agent framework (MDA) combining an LLM proposer with Sequential Monte Carlo (SMC) and Simulation-Based Inference (SBI), extended to the 𝓜-open regime.

The research achieves a new SOTA on two existing scientific discovery benchmarks in physics and chemistry, maintaining the same accuracy while requiring significantly fewer experiments. Additionally, the author releases NeuronBench, a new partially-observed, stochastic electrophysiology benchmark. A talk on this work is scheduled for the "RL in Big Worlds" workshop at RLC in Montreal on August 15.

Related event: Google's MDA Combines LLMs and Bayesian Inference to Accelerate Scientific Discovery(4 posts)→

Original post →

More from Research

Research channel →