GOLLuM finds 36.3% of top-5% outcomes vs 29.7% for descriptor-based optimization
pschwllr · x · 2026-10-02
GOLLuM pairs a language model with a Gaussian process to choose the next experiment. Across 23 retrospective benchmarks from Schwaller's group, its main variant found 36.3% of top-5% outcomes versus 29.7% for descriptor-based optimization. These were dataset searches, not lab trials.
More from Research
- Berating LLMs makes their internal pain axis light up even as they apologize, study finds — repligate · 2026-10-02
- Micah Goldblum's team releases new paper with open models, code and website — micahgoldblum · 2026-10-02
- Pinocchio: an external calibrator brings fast uncertainty estimates to black-box LLM APIs — micahgoldblum · 2026-10-02
- Pinocchio works across API models and transfers zero-shot to unseen LLMs, authors note — micahgoldblum · 2026-10-02
- Pinocchio: a lightweight model that adds calibrated confidence to frontier LLM outputs — micahgoldblum · 2026-10-02
- Extropic claims 100x-10,000x efficiency in first results on thermodynamic recursive intelligence — beffjezos · 2026-10-02