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.
More from Research
- MLCommons launches MLPerf Endpoints, a benchmark that measures inference endpoints the way buyers actually purchase them — TheKanter · 2026-10-16
- DIY LEGO bench tests AI brick-building, GPT-6 Astra beats Opus — TheLegoless · 2026-10-16
- tszzl's theory: Tornado → Apache license → apaches → Southwest → Colorado — tszzl · 2026-10-16
- DIRECT: retrieval-based next-question suggestions for conversational agents — burkov · 2026-10-16
- A Qwen3 neuron tracks both Colorado and Tornado HTTP code; tszzl offers a theory — tszzl · 2026-10-16
- AI-Driven Timing-Aware Power Optimization Uses Learned Ranking With Baseline-Preserving Repair — Amit Sharma · 2026-10-16