Abductive Computational Systems: Creative Abduction and Future Directions
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Abductive reasoning, reasoning for inferring explanations for observations, is often mentioned in scientific, design-related and artistic contexts, but its understanding varies across these domains. This paper reviews how abductive reasoning is discussed in epistemology, science and design, and then analyses how various computational systems use abductive reasoning. Our analysis shows that neither theoretical accounts nor computational implementations of abductive reasoning adequately address generating creative hypotheses. Theoretical frameworks do not provide a straightforward model for generating creative abductive hypotheses, computational systems largely implement syllogistic forms of abductive reasoning. We break down abductive computational systems into components and conclude by identifying specific directions for future research that could advance the state of creative abductive reasoning in computational systems.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 7 of its 30 references that are in the map. First posted on arXiv 11 Jul 2025.
Builds on
7 of 30 references.
References · 7
- 2017Attention Is All You Needcited by 59,932
- 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
- 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
- 2019Abductive Commonsense Reasoningcited by 300
- 2023Benchmarking Cognitive Biases in Large Language Models as Evaluatorscited by 147
- 2022Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systemscited by 59
- 2023MacGyver: Are Large Language Models Creative Problem Solvers?cited by 33
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
- 2025GEAR: A General Evaluation Framework for Abductive Reasoning
- 2023Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
- 2024Abductive Symbolic Solver on Abstraction and Reasoning Corpus
- 2026Graph of States: Solving Abductive Tasks with Large Language Models
- 2022AbductionRules: Training Transformers to Explain Unexpected Inputs
- 2026Propositional Abduction via Only-Knowing: A Non-Monotonic Approach
- 2026DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models