mlsanityData to 14 Oct 2026

Thought without systematicity? Evaluating reasoning models on rule induction tasks

arXiv 2609.13948 ↗First posted 12 Sep 2026cs.CL cs.AI cs.LGcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 24 of its 53 references that are in the map. First posted on arXiv 12 Sep 2026.

Builds on

24 of 53 references.

References · 24

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  8. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  9. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  10. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  11. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  12. 2019How Can We Know What Language Models Know?cited by 959
12 more
  1. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  2. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  3. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  4. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  5. 2019Compositionality decomposed: how do neural networks generalise?cited by 265
  6. 2023Consistency Analysis of ChatGPTcited by 37
  7. 2026Brittlebench: Quantifying LLM robustness via prompt sensitivitycited by 21
  8. 2024Attention as a Hypernetworkcited by 13
  9. 2025Metamorphic Testing of Large Language Models for Natural Language Processingcited by 12
  10. 2025SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Factscited by 8
  11. 2026Measuring Progress Toward AGI: A Cognitive Frameworkcited by 6
  12. 2026LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scalingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures
  2. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
  3. 2025A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gap
  4. 2026To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
  5. 2025Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
  6. 2025How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects
  7. 2025Cognitive Foundations for Reasoning and Their Manifestation in LLMs
  8. 2026NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries