cs.AINov 15, 2026

Asking the right question is key to AI discovery in a chain of hypotheses

Authors: Hu Cang

Organizations: Department of Developmental and Cell Biology, University of California, Irvine, CA 92697, USA.

Abstract

Artificial intelligence (AI) scientists pursue discovery through a chain of hypotheses, fitting candidate models to existing observations and often choosing experiments where those models disagree most. Yet when early data miss a narrow feature, model selection favors simple curves that agree across the unmea- sured gap, so disagreement-guided search has no reason to look where the new phenomenon lies. When we tested two frontier AI scientists, Claude Sonnet 5.5 and GPT-6.1-Sol, across 32 closed-loop trials with a narrow peak omitted from the starting data, both sampled inside the peak region less often than random search. Surprisingly, the agent that followed model disagreement more closely missed the peak in all 32 trials, whereas discovery succeeded when experiments probed the unmeasured gap early and followed up across the anomaly. Asking the right question, rather than testing only where current models disagree, is therefore key to AI discovery in a chain of hypotheses.

Figures & tables

Explore similar work

CardsList
  1. A Three-Layer Framework for AI in Scientific Discovery

    Jun 11, 2026Guojun LiaoAI for ScienceScientific Reasoning

  2. Position: Correct Answer, Wrong Mechanism -- When AI Scientists Defend General Claims Their Own Data Contradicts

    Jun 22, 2026Steven Young EuligAI Agent ReliabilityReasoning Evaluation