# Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind

arXiv: https://arxiv.org/abs/2603.26089 · HTML: https://mlsanity.com/paper/2603.26089/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [Understanding Social Reasoning in Language Models with Language Models](https://mlsanity.com/paper/2306.15448/) (2023)
- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [ToMBench: Benchmarking Theory of Mind in Large Language Models](https://mlsanity.com/paper/2402.15052/) (2024)
- [Evaluating Theory of Mind in Question Answering](https://mlsanity.com/paper/1808.09352/) (2018)
- [LLMs achieve adult human performance on higher-order theory of mind tasks](https://mlsanity.com/paper/2405.18870/) (2024)
- [SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs](https://mlsanity.com/paper/2410.13648/) (2024)
- [Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models](https://mlsanity.com/paper/2310.19619/) (2023)
- [Language Models Represent Beliefs of Self and Others](https://mlsanity.com/paper/2402.18496/) (2024)
- [Position: Theory of Mind Benchmarks are Broken for Large Language Models](https://mlsanity.com/paper/2412.19726/) (2024)
- [Re-evaluating Theory of Mind evaluation in large language models](https://mlsanity.com/paper/2502.21098/) (2025)
- [Evidence for Limited Metacognition in LLMs](https://mlsanity.com/paper/2509.21545/) (2025)
- [MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning](https://mlsanity.com/paper/2411.12977/) (2024)
- [MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents](https://mlsanity.com/paper/2511.23055/) (2025)

## Built on by (most cited first, 2 of 2)

- [PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://mlsanity.com/paper/2606.08878/) (2026)
- [When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models](https://mlsanity.com/paper/2606.22974/) (2026)

## Abstract (arXiv)

The ability to represent oneself and others as agents with knowledge, intentions, and belief states that guide their behavior - Theory of Mind - is a human universal that enables us to navigate - and manipulate - the social world. It is supported by our ability to form mental models of ourselves and others. Its ubiquity in human affairs entails that LLMs have seen innumerable examples of it in their training data and therefore may have learned to mimic it, but whether they have actually learned causal models that they can deploy in arbitrary settings is unclear. We therefore develop a novel experimental paradigm that requires that subjects form representations of the mental states of themselves and others and act on them strategically rather than merely describe them. We test a wide range of leading open and closed source LLMs released since 2024, as well as human subjects, on this paradigm. We find that 1) LLMs released before mid-2025 fail at all of our tasks, 2) more recent LLMs achieve human-level performance on modeling the cognitive states of others, and 3) even frontier LLMs fail at our self-modeling task - unless afforded a scratchpad in the form of a reasoning trace. We further demonstrate cognitive load effects on other-modeling tasks, offering suggestive evidence that LLMs are using something akin to limited-capacity working memory to hold these mental representations in mind during a single forward pass. Finally, we explore the mechanisms by which reasoning models succeed at the self- and other-modeling tasks, and show that they readily engage in strategic deception.