LLM Finds Interesting Theorems With 4.3x Higher Interestingness
The shift here is from LLMs as proof-checkers to LLMs as autonomous curators of what counts as a meaningful result, with interestingness turned into a measurable objective. Researchers in automated theorem proving and AI-for-math can borrow the quantitative framing to evaluate their own discovery pipelines. It contrasts with purely benchmark-driven evaluation, where correctness exists but relevance does not.
Niket Patel shared a research thread on X arguing that LLMs are now proving mathematical results that have resisted mathematicians for decades.
The work introduces a quantitative notion of "interestingness" for theorems.Using it, the authors report a 4.
3x increase in interestingness of found theorems.The system is built as a self-expanding discovery loop, and a stated new bottleneck is finding interesting theorems without human guidance.
this is important Niket Patel @niketnpatel “An accumulation of facts is no more a science than a heap of stones is a house.” - Poincaré LLMs are now proving results that have resisted mathematicians for decades. Finding interesting theorems without human guidance is a new bottleneck. We show that we can teach an LLM to do it! TL;DR: → a quantitative notion of interestingness → 4.3× higher interestingness → a self-expanding discovery loop [1/5] 🔗 View Quoted Tweet
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LLM, reasoning models, automated theorem proving, research.
Source attribution: curated from Thomas Wolf (@Thom_Wolf).