Abductive Reasoning & the Limits of AI Discovery
Peirce's third mode of inference — generating a novel explanatory hypothesis or axiom (Rule+Result → Case) to account for a surprising result — argued to be structurally missing from current LLMs, which have mastered induction and deduction but lack the embodied/simulation-grounded mechanism needed to invent axioms under data scarcity.
Also known as: abduction, Abduction (Peirce), abductive reasoning, abductive leap, the Jump, inference to the best explanation, manipulative abduction, creativity as compression, axiom generation
Part of: LLM Limitations
How authors use it
Oldest first (extraction date when no publication date is known).
| Author | Their term | Their meaning |
|---|---|---|
| LLMs Can't Jump Tom Zahavy, Google DeepMind · 2026-05-23 | The Jump (J) | The intuitive, non-logical cognitive leap Einstein described in his letter to Solovine connecting Sense Experience (E) to a System of Axioms (A) — the specific act the paper argues LLMs cannot perform. |
| LLMs Can't Jump Tom Zahavy, Google DeepMind · 2026-05-23 | Abduction | Following Peirce: inference of a Case (or new Rule) from a Rule and a surprising Result (Rule+Result -> Case) — a creative leap that invents a cause for a singular phenomenon, distinct from both deduction (guarantees truth) and induction (finds statistical patterns). |
| LLMs Can't Jump Tom Zahavy, Google DeepMind · 2026-05-23 | Manipulative Abduction | Magnani's (2009) concept: abduction driven by active, embodied interaction with mental models ('thinking by doing') rather than passive symbolic search — e.g., Einstein simulating the physical sensation of falling. |
| LLMs Can't Jump Tom Zahavy, Google DeepMind · 2026-05-23 | Creativity as Compression | Schmidhuber's (2008) theory that scientific discovery is driven by the inductive desire to compress data — the 'joy' of discovery being the rate at which complex observations become subjectively simpler. Used in this paper as the rival theory being refuted. |
Documents (1)
- LLMs Can't Jump Tom Zahavy, Google DeepMind · 2026-05-23 source ↗ Reader 🖥️
Modern LLMs have mastered Induction (statistical pattern-matching) and are rapidly mastering Deduction (formal proof), but are structurally incapable of Abduction — the embodied-simulation-grounded leap from scarce sense experience to novel explanatory axioms that produced discoveries like General Relativity — so genuine AI scientific invention requires physically-consistent, interactive, multimodal world models rather than more language-model scale.
Propositions touching this concept (3)
By publication month, oldest first (extraction month when no publication date is known).
2026-05
- explicitLLMs have mastered Induction (statistical pattern matching from data) and are rapidly mastering Deduction (formal derivation/proof, e.g. AlphaProof, Lean-based theorem proving), but are structurally incapable of Abduction — the generation of novel explanatory hypotheses or axioms.
- explicitThe critical bottleneck is translating embodied, simulated physical experience into formal axioms, exemplified by Einstein's 'happiest thought' (the falling-observer/elevator thought experiment), which relied on manipulative abduction — grounding abstract symbols in simulated sensory experience rather than manipulating pre-existing symbols.
- implicitVerifiable, RL-optimizable domains (formal proof, code) are where LLM capability gains concentrate, while abduction-requiring domains structurally lack a clean error/reward signal — meaning current RL-based scaling recipes cannot, by their own logic, be expected to close the abductive gap.
Open gaps (3)
- incompleteThe paper's positive proposal -- that action-controllable, physically-consistent multimodal world models will supply the sensory grounding needed for abduction -- is asserted but not operationalized. No benchmark, no success criterion, and critically, no account of how a 'counterfactual physical simulation' would itself get translated into a formal axiom: translation-from-simulation-to-axiom is exactly the bottleneck the paper identifies as the Jump, and it recurs unaddressed inside the proposed solution rather than being solved by it.LLMs Can't Jump — read next: Genie / Genie 2 / Genie 3 technical reports and any successor work on translating interactive world-model states into formal symbolic theories; LeCun's JEPA and world-model architecture papers for how (or whether) symbol grounding is actually operationalized there.
- incompleteThe entire argument rests on one historical case (Einstein/General Relativity), reconstructed via a single secondary source (Norton, 2020). No comparison is made to other major discoveries made under data scarcity -- Darwin's natural selection, Wegener's continental drift, Mendel's genetics -- to test whether 'manipulative abduction via embodied simulation' is the general mechanism of discovery-under-scarcity or an idiosyncrasy of how Einstein specifically thought (he is quoted saying words play no role in his mechanism of thought -- a documented personal trait, not obviously evidence about scientific discovery in general).LLMs Can't Jump — read next: Case studies of scientific discovery in non-physics domains (biology, geology) under comparable data scarcity, to test whether the embodied-simulation account generalizes or is Einstein-specific.
- illogicalThe paper concedes that an AI could plausibly identify the conceptual inconsistency between Newtonian absolute time and Maxwell's constant speed of light that motivated Einstein's search in the first place -- an act of noticing which surprising Result is worth explaining. Yet the paper classifies this act as merely deductive ('much like a system identifying buggy code'), while its own Peircean framework defines exactly this kind of selection (choosing which Case merits explanation) as characteristically abductive. This blurs the sharp induction/deduction/abduction boundary the paper otherwise insists on, without acknowledging the tension.LLMs Can't Jump — read next: Peirce's own writing on abduction as hypothesis-selection (not just hypothesis-generation) would clarify whether 'noticing an inconsistency worth resolving' counts as abduction under his original scheme.