Reasoning Promotes Robustness in Theory of Mind Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911394047197184 |
|---|---|
| author | de Haan, Ian B. van der Putten, Peter van Duijn, Max |
| author_facet | de Haan, Ian B. van der Putten, Peter van Duijn, Max |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16853 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reasoning Promotes Robustness in Theory of Mind Tasks de Haan, Ian B. van der Putten, Peter van Duijn, Max Artificial Intelligence Computation and Language 68T50 (Primary), 68T01 (Secondary) I.2.7; I.2.0 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. |
| title | Reasoning Promotes Robustness in Theory of Mind Tasks |
| topic | Artificial Intelligence Computation and Language 68T50 (Primary), 68T01 (Secondary) I.2.7; I.2.0 |
| url | https://arxiv.org/abs/2601.16853 |