Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game
[Sztuczna inteligencja] Autorzy: Muhan Gao, Hangxiao Zhu, Xinqi Su i 3 więcej
Research ideation is iterative: researchers refine their ideas step by step based on feedback. Yet existing evaluations obscure this search process, making it difficult to understand how LLMs explore the space of research ideas and what limits their progress. We introduce Re-Search, which adapts the format of Twenty Questions to research ideation: given only the research problem of a published paper, a model must rediscover the paper's core idea by asking yes-or-no questions. Built from 200 ICML 2026 papers, Re-Search tracks how a model's idea evolves as it asks questions and receives binary oracle feedback, isolating ideation from execution. Across six recent LLMs, nearly all progress happens within the first 30 of 100 questions, which largely decide how the game ends; after that, most models plateau. Through controlled interventions on the candidate questions and the hypothesis space,…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja