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
- IndexTTS 2.5 Launches: 2.28x Faster Inference and Zero-Shot Cross-Lingual Emotion Transfer — Xianbao_QIAN · 2026-08-12
- Revisiting the $10.7M THORChain Hack with LLMs: Cryptographic Flaws Explained — banteg · 2026-08-12
- New ViT Anime Tagger Beats WD-tagger v3 by +0.053 mAP — darkth0ughts · 2026-08-12
- Why AI Needs Memory Engineering: Graph Memory Beats Flat Vector Stores — anirbanbandyo · 2026-08-12
- LlamaIndex Launches ExtractBench: 4,869 Pages of Complex Docs Across 8 Domains — llama_index · 2026-08-12
- Mitsuhiko Calls for More Direct Criticism Over Academic 'Glass Hearts' — cloneofsimo · 2026-08-12