Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation
2026-08-03 • Artificial Intelligence
Artificial IntelligenceComputer Vision and Pattern RecognitionInformation Retrieval
AI summaryⓘ
The authors explore whether creating new scientific hypotheses always needs an agent to be physically connected to the world. They focus on 'identity abduction,' which means realizing two different structures are actually the same thing, based on representations rather than physical interaction. They propose using scientific diagrams as a shared language to find connections across different fields, implemented in a system called the Abduction Loop. They demonstrate this idea with a case where a model linked concepts from gravity and cosmology, and suggest ways to test their approach in the future.
Scientific abductionSensorimotor embodimentIdentity abductionRepresentational groundingScientific diagramsConvention spaceCross-domain retrievalAdversarial verificationWeak-lensing cosmologyAbduction Loop architecture
Authors
Michael Farmer
Abstract
Can scientific abduction occur without continuous sensorimotor embodiment? Recent arguments in AI and philosophy of science hold that genuine hypothesis generation requires an agent continuously coupled to the physical world. We defend a narrower claim: online embodiment is not necessary for every abductive scientific act. Our focus is identity abduction: the inference that two independently developed structures are one object under an explicit correspondence, reached through representational grounding rather than bodily interaction. An agent may acquire new inferential affordances not through physical interaction but through transformations into representations that expose latent invariants. Scientific diagrams are a practical substrate because they embody independently evolved conventions that partially canonicalize symmetry, topology, and operator structure across disciplines - a property we develop as convention space, which answers a hard retrieval problem: finding mathematically related work when two fields share no discriminating vocabulary. We operationalize the mechanism as an architecture, the Abduction Loop: representation generation, motif extraction, convention-space canonicalization, cross-domain retrieval, identity-hypothesis generation, and adversarial verification, with abstention as the designed default. A documented episode, in which a multimodal model given a figure of a gravitational-memory transport model generated and then verified the hypothesis that its central differential complex is equivalent to the spherical Kaiser-Squires mass-mapping complex of weak-lensing cosmology, serves as a motivating possibility witness from which the architecture is abstracted, not as evidence of general capability. We close with a falsifiable evaluation program, the DAB-30 benchmark. The contribution is a mechanistic proposal, an architecture, and a test program.