Particles of Thought at COLM 2026: Sequential Monte Carlo unifies process supervision and test-time search
jwvdm · x · 2026-10-08
At the Efficient Reasoning workshop at COLM 2026, researchers presented Particles of Thought (with Max Welling et al.): aligning process supervision with test-time search by applying Sequential Monte Carlo (SMC) at both training and inference time.
It's a new approach to combining process-reward-style supervision with inference-time compute, part of the efficient reasoning research line.
More from Research
- Stanford's Anshul Kundaje Skeptical of 'Universal Virtual Cell': Models Must Be Grounded in Real Biology — anshulkundaje · 2026-10-08
- Kernaut: coding agents design Gaussian process kernels via program search — sirbayes · 2026-10-08
- Kernaut's discovered kernels stay interpretable: 16 scalar functions, inner-product form — sirbayes · 2026-10-08
- iOSWorld brings computer-use agent benchmarking to iOS at COLM 2026 — kohjingyu · 2026-10-08
- Epoch's InnovationEval: AI agents still far from producing real research innovations — Afinetheorem · 2026-10-08
- Dankrad: AI's inelegant math results reveal human bias from small context windows — CatAstro_Piyush · 2026-10-08