mlsanityData to 7 Oct 2026

Reasoning Promotes Robustness in Theory of Mind Tasks

arXiv 2601.16853 ↗First posted 23 Jan 2026cs.AI cs.CLcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large language models (LLMs) have recently shown strong performance on Theory of Mind (ToM) tests, prompting debate about the nature and true performance of the underlying capabilities. At the same time, reasoning-oriented LLMs trained via reinforcement learning with verifiable rewards (RLVR) have achieved notable improvements across a range of benchmarks. This paper examines the behavior of such reasoning models in ToM tasks, using novel adaptations of machine psychological experiments and results from established benchmarks. We observe that reasoning models consistently exhibit increased robustness to prompt variations and task perturbations. Our analysis indicates that the observed gains are more plausibly attributed to increased robustness in finding the correct solution, rather than to fundamentally new forms of ToM reasoning. We discuss the implications of this interpretation for evaluating social-cognitive behavior in LLMs.

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 18 of its 40 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

18 of 40 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models17 Feb
  2. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models16 Jan
  3. 2023Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities16 Nov

Other references · 15

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  5. 2023A Survey of Large Language Modelscited by 2,537
  6. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  7. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
  8. 2025Reasoning Models Don't Always Say What They Thinkcited by 388
  9. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  10. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 217
  11. 2022Will we run out of data? Limits of LLM scaling based on human-generated datacited by 187
  12. 2023FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactionscited by 162
3 more
  1. 2024LLMs achieve adult human performance on higher-order theory of mind taskscited by 59
  2. 2025Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasonerscited by 22
  3. 2025DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logiccited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning
  2. 2024Probing the Robustness of Theory of Mind in Large Language Models
  3. 2025Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?
  4. 2026To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
  5. 2026Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models
  6. 2023Studying and improving reasoning in humans and machines
  7. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models
  8. 2023Understanding Social Reasoning in Language Models with Language Models