Priced Guidance: quantifying whether LLMs can generate novel research ideas via compression
stanfordnlp · x · 2026-10-07
A new paper proposes Priced Guidance, which quantifies whether LLMs can produce novel research ideas via compression. Instead of sampling ideas until a future paper's idea X is matched, the LLM plays "20 Questions" to recover X, charging each hint by its surprisal — lower-bounding the probability that an LLM can forecast a future paper's idea. Commenters highlight it as an elegant information-theoretic probe with applications far beyond AI ideation.
Related event: Priced Guidance: Quantifying Whether LLMs Can Generate Novel Research Ideas(2 posts)→
More from Research
- GEA treats agent groups as the evolution unit, hitting 71% SWE-bench Verified with zero human help — xwang_lk · 2026-10-07
- 9B model fine-tuned with ~$25 of compute hits 79% of Jev's Decision Index score — sophiamyang · 2026-10-07
- Recovery skills lift real-robot task success from 77.5% to 87.5% in Recova — qinzytech · 2026-10-07
- Self-supervised learning automates thyroid cytology image feature analysis — zakkohane · 2026-10-07
- An excellent overview of AI watermarking and why it can't really be avoided — aronchick · 2026-10-07
- Self-improving agent Steve masters Minecraft unaided, out-progressing 97% of human players — julianweisser · 2026-10-07