2025/06/30 by András György, Tor Lattimore, György, András +5 · 2 voices · 5 citations
Computer Science · Decision Sciences · #Algorithmic learning theory #Artificial general intelligence #Correctness #Deductive reasoning #Defeasible reasoning #Explainable Artificial Intelligence (XAI) #Forecasting Techniques and Applications #Machine Learning and Algorithms #Model-based reasoning #Qualitative reasoning #Reasoning system #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2506.23908
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/06/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Sound deductive reasoning -- the ability to derive new knowledge from existing facts and rules -- is an indisputably desirable aspect of general intelligence. Despite the major advances of AI systems in areas such as math and science, especially since the introduction of transformer architectures, it is well-documented that even the most advanced frontier systems regularly and consistently falter on easily-solvable deductive reasoning tasks. Hence, these systems are unfit to fulfill the dream of achieving artificial general intelligence capable of sound deductive reasoning. We argue that their unsound behavior is a consequence of the statistical learning approach powering their development. To overcome this, we contend that to achieve reliable deductive reasoning in learning-based AI systems, researchers must fundamentally shift from optimizing for statistical performance against distributions on reasoning problems and algorithmic tasks to embracing the more ambitious exact learning paradigm, which demands correctness on all inputs. We argue that exact learning is both essential and possible, and that this ambitious objective should guide algorithm design.