# TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mind

arXiv: https://arxiv.org/abs/2407.01455 · HTML: https://mlsanity.com/paper/2407.01455/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 1 Jul 2024.

## Builds on (most cited first, 18 of 18)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Understanding Social Reasoning in Language Models with Language Models](https://mlsanity.com/paper/2306.15448/) (2023)
- [FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions](https://mlsanity.com/paper/2310.15421/) (2023)
- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [Solving Math Word Problems by Combining Language Models With Symbolic Solvers](https://mlsanity.com/paper/2304.09102/) (2023)
- [Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker](https://mlsanity.com/paper/2306.00924/) (2023)
- [Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities](https://mlsanity.com/paper/2311.10227/) (2023)
- [Evaluating Theory of Mind in Question Answering](https://mlsanity.com/paper/1808.09352/) (2018)
- [Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning](https://mlsanity.com/paper/2312.05230/) (2023)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others](https://mlsanity.com/paper/2102.11938/) (2021)
- [A World-Self Model Towards Understanding Intelligence](https://mlsanity.com/paper/2203.13762/) (2022)

## Built on by (most cited first, 21 of 21)

- [MuMA-ToM: Multi-modal Multi-Agent Theory of Mind](https://mlsanity.com/paper/2408.12574/) (2024)
- [Language Models use Lookbacks to Track Beliefs](https://mlsanity.com/paper/2505.14685/) (2025)
- [Theory of Mind in Large Language Models: Assessment and Enhancement](https://mlsanity.com/paper/2505.00026/) (2025)
- [AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling](https://mlsanity.com/paper/2502.15676/) (2025)
- [EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective](https://mlsanity.com/paper/2410.06195/) (2024)
- [Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind](https://mlsanity.com/paper/2502.21297/) (2025)
- [Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer](https://mlsanity.com/paper/2410.24155/) (2024)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States](https://mlsanity.com/paper/2503.03340/) (2025)
- [ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions](https://mlsanity.com/paper/2509.05066/) (2025)
- [Let's Put Ourselves in Sally's Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Models](https://mlsanity.com/paper/2506.05970/) (2025)
- [Beyond Words: Evaluating and Bridging Epistemic Divergence in User-Agent Interaction via Theory of Mind](https://mlsanity.com/paper/2602.13832/) (2026)
- [Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations](https://mlsanity.com/paper/2605.15205/) (2026)
- [UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind](https://mlsanity.com/paper/2605.27721/) (2026)
- [TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence](https://mlsanity.com/paper/2505.24500/) (2025)
- [EvolvTrip: Enhancing Literary Character Understanding with Temporal Theory-of-Mind Graphs](https://mlsanity.com/paper/2506.13641/) (2025)
- [Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning](https://mlsanity.com/paper/2510.07974/) (2025)
- [CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models](https://mlsanity.com/paper/2604.10031/) (2026)
- [MindZero: Learning Online Mental Reasoning With Zero Annotations](https://mlsanity.com/paper/2606.00240/) (2026)
- [PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters' Lack of Knowledge](https://mlsanity.com/paper/2608.01598/) (2026)
- [Beyond Belief Nesting: Rethinking Higher-Order Theory of Mind in Large Language Models](https://mlsanity.com/paper/2610.17777/) (2026)

## Abstract (arXiv)

Theory of Mind (ToM)-the cognitive ability to reason about mental states of ourselves and others, is the foundation of social interaction. Although ToM comes naturally to humans, it poses a significant challenge to even the most advanced Large Language Models (LLMs). Due to the complex logical chains in ToM reasoning, especially in higher-order ToM questions, simply utilizing reasoning methods like Chain of Thought (CoT) will not improve the ToM capabilities of LLMs. We present TimeToM, which constructs a temporal space and uses it as the foundation to improve the ToM capabilities of LLMs in multiple scenarios. Specifically, within the temporal space, we construct Temporal Belief State Chain (TBSC) for each character and inspired by the cognition perspective of the social world model, we divide TBSC into self-world beliefs and social world beliefs, aligning with first-order ToM (first-order beliefs) and higher-order ToM (higher-order beliefs) questions, respectively. Moreover, we design a novel tool-belief solver that, by considering belief communication between characters in temporal space, can transform a character's higher-order beliefs into another character's first-order beliefs under belief communication period. Experimental results indicate that TimeToM can dramatically improve the reasoning performance of LLMs on ToM questions while taking a big step towards coherent and robust ToM reasoning.