Researchers teach LLMs to find interesting theorems, boosting interestingness 4.3x
CatAstro_Piyush · x · 2026-09-26
A new research thread argues that while LLMs can now prove results that resisted mathematicians for decades, finding interesting theorems without human guidance is the new bottleneck. The team introduces a quantitative notion of "interestingness," trains an LLM to optimize for it—achieving 4.3x higher interestingness—and builds a self-expanding discovery loop.
More from Research
- Claude reportedly computes a nine-loop scattering amplitude, topping the eight-loop record — Dr_Singularity · 2026-09-26
- Cadence: An Architecture for a Continuous, Efficient Stream of Intelligence — rvp · 2026-09-26
- Dev trains a 50MB model in 15 min to replace Gemini Flash at 0.06s latency — newz2000 · 2026-09-26
- WetLabs Benchmark tests robots on 9 wet-lab tasks: can machines accelerate science? — ericjang11 · 2026-09-26
- Medmarks v1.0 lands NeurIPS track: medical LLM benchmark now covers 30 suites, 61 models — iScienceLuvr · 2026-09-26
- AI-driven lab finds iridium-free palladium catalyst InMnPdOx stable for 1,000 hours — CatAstro_Piyush · 2026-09-26