MDA by Kevin Murphy: LLMs Meet Bayesian Inference for Scientific Discovery
sirbayes · x · 2026-08-12
A new paper by Kevin Murphy introduces the Model Discovery Agent (MDA), a framework combining LLMs with Bayesian experimental design. MDA uses an LLM as a proposer for candidate structures and standard Bayesian machinery like Sequential Monte Carlo (SMC) and Simulation-Based Inference (SBI) to discover latent mechanistic world models.
Key contributions include:
- MDA Framework: Couples LLMs with Bayesian methods for data-efficient discovery, extended to the M-open regime where the truth lies outside the current hypothesis class.
- New SOTA: Achieves state-of-the-art accuracy on existing physics and chemistry benchmarks with significantly fewer experiments.
- NeuronBench: Introduces a new partially-observed, stochastic electrophysiology benchmark.
The paper also explains how the learned summary avoids representational collapse by anchoring through a supervised objective, adapting freely to whatever channels the LLM proposes.
More from Research
- Experiments Show Tensor-Train Decomposition Tractably Models High-Dimensional Data — kalomaze · 2026-08-12
- 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