Research
Thought without systematicity? Evaluating reasoning models on rule induction tasks
arXiv:2609.13948v1 Announce Type: cross Abstract: A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to understanding close variations
arXiv:2609.13948v1 Announce Type: cross Abstract: A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to understanding close variations of that concept. Do reasoning models robustly exhibit such systematicity? If so, we would expect consistent performance on structurally equivalent variants of the same task. Here, we extend established rule induction tasks from cognitive science to assess the systematicity of thought in current reasoning models. Each task family has compositional structure that we use to create structurally equivalent task variations through task isomorphisms such as recombination and substitution. We find that despite being able to correctly solve a task, models often fail on structurally equivalent variants of the same task. These findings suggest that many model behaviors lack systematicity, rendering it difficult to robustly establish the cognitive abilities of reasoning models beyond the particular contexts they were evaluated in.
Related
- Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory
- ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning
- Doesn't Stop Reasoning: Analysis of Spurious CoT Termination
- When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large Language Models
Source: arXiv cs.AI | 2026-09-15