mlsanityData to 14 Oct 2026

Position: Reasoning is a Learnable Rule-Based Process

arXiv 2608.12325 ↗First posted 29 May 2026cs.AI cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent advances have mainly emerged from deep probabilistic generative models. Despite immense interest and rapid progress, the generative AI community has not clearly converged on operational definitions for reasoning and often implicitly rejects the historical treatment of this topic in logic and verifiable automated reasoning. This position contends that definitional ambiguity leaves the construct validity of reasoning evaluation unverifiable, undermining quantifiable progress toward trustworthy autonomous reasoning. We also contend that this ambiguity is addressable. To that end, we provide (1) operational definitions based on a synthesis of the literature, positioning valid and sound reasoning as a learnable rule-based process; and (2) a checklist for best practices in the communication of AI reasoning research.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 66 of its 157 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

66 of 157 references.

References · 66

  1. 2020Scaling Laws for Neural Language Modelscited by 6,586
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  4. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  5. 2022Emergent Abilities of Large Language Modelscited by 2,512
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  8. 2025s1: Simple test-time scalingcited by 1,341
  9. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  10. 2022In-context Learning and Induction Headscited by 964
  11. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  12. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 703
38 more
  1. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  2. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  3. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 550
  4. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  5. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  6. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  7. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
  8. 2023Faithful Chain-of-Thought Reasoningcited by 288
  9. 2022Transformers Learn Shortcuts to Automatacited by 268
  10. 2024LiveBench: A Challenging, Contamination-Limited LLM Benchmarkcited by 262
  11. 2024DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Datacited by 234
  12. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 218
  13. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 207
  14. 2021What Will it Take to Fix Benchmarking in Natural Language Understanding?cited by 203
  15. 2023How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language modelcited by 202
  16. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 196
  17. 2025Open Problems in Mechanistic Interpretabilitycited by 179
  18. 2025Hierarchical Reasoning Modelcited by 177
  19. 2021Saturated Transformers are Constant-Depth Threshold Circuitscited by 139
  20. 2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!cited by 132
  21. 2024ARC Prize 2024: Technical Reportcited by 104
  22. 2025Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2cited by 97
  23. 2023Levels of AGI for Operationalizing Progress on the Path to AGIcited by 96
  24. 2024The Surprising Effectiveness of Test-Time Training for Few-Shot Learningcited by 96
  25. 2026Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Modelscited by 86
  26. 2024Robust agents learn causal world modelscited by 81
  27. 2025Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thoughtcited by 77
  28. 2025Position: Evaluating Generative AI Systems Is a Social Science Measurement Challengecited by 63
  29. 2024Combining Induction and Transduction for Abstract Reasoningcited by 53
  30. 2023Lemur: Integrating Large Language Models in Automated Program Verificationcited by 49
  31. 2025Toward an Evaluation Science for Generative AI Systemscited by 45
  32. 2025Medical Large Language Model Benchmarks Should Prioritize Construct Validitycited by 38
  33. 2025Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGIcited by 36
  34. 2015Neural Programmer: Inducing Latent Programs with Gradient Descentcited by 34
  35. 2025Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewardscited by 34
  36. 2024Hypothesis Testing the Circuit Hypothesis in LLMscited by 29
  37. 2025A Definition of AGIcited by 27
  38. 2024The Clever Hans Effect in Unsupervised Learningcited by 24

50 most cited of 66 All 66 (JSON)

Built on by

Not cited yet.