Theory framework explains when prover-conjecturer self-play lets LLMs self-improve at theorem proving
stanfordnlp · x · 2026-11-09
Inspired by STP (Dong & Ma, 2025), Thomas proposes a theoretical framework for understanding when prover-conjecturer self-play algorithms can enable LLM self-improvement at theorem proving.
The work is accepted as a NeurIPS 2026 poster (Sydney), presented Tue 5-8pm at Hall 1-4, Poster Session 2. Stanford NLP amplified the thread, calling it cool theory on when self-improvement via self-play is possible.
More from Research
- Stanford team teaches an AI agent a pool table's physics by letting it take real shots (CoRL) — drmapavone · 2026-11-09
- Furong Huang Lab brings six human-video-to-robot works to CoRL 2026 — furongh · 2026-11-09
- FOCS paper: membership inference attacks can need far more reference samples than training data — roydanroy · 2026-11-09
- Pallatom2: a 65.9M-param atom-level protein design model hits 53.3% experimental success rate — sokrypton · 2026-11-09
- AI has broken science's main evaluation proxy, argues computational biologist — anshulkundaje · 2026-11-09
- Learning is compression: a long-form essay on manifold hypothesis and why intelligence is possible at all — burny_tech · 2026-11-09