Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most systems remain pointwise: they evaluate one candidate hypothesis at a time for surprise, novelty, or evidential support. This is information-inefficient: rejecting a hypothesis reveals that one explanation is unlikely, but not which alternatives are better supported. We argue that the proper epistemic unit of discovery is not a single hypothesis but a scientific question together with the mutually exclusive and collectively exhaustive (MECE) explanations that could answer it. We introduce Contrastive Discovery, which scores candidate discoveries by how evidence redistributes belief across competing explanations. This allows a single experiment to both rule out hypotheses and identify the most plausible alternative. Across six scientific domains, Contrastive Discovery yields substantially more resolved scientific questions than pointwise baselines under the same evidence-generation budget. Among top pointwise-surprisal candidates, 89% are rejected; on the identical evidence, representing explicit alternatives instead resolves 73% to a specific competing explanation. These gains come almost entirely from corrective updates, showing that an explicit representation of alternatives turns the negative evidence that pointwise discovery discards into resolved scientific questions.