# AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling

arXiv: https://arxiv.org/abs/2502.15676 · HTML: https://mlsanity.com/paper/2502.15676/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 21 Feb 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [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)
- [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)
- [MMToM-QA: Multimodal Theory of Mind Question Answering](https://mlsanity.com/paper/2401.08743/) (2024)
- [Online Bayesian Goal Inference for Boundedly-Rational Planning Agents](https://mlsanity.com/paper/2006.07532/) (2020)
- [HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models](https://mlsanity.com/paper/2310.16755/) (2023)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Automated Statistical Model Discovery with Language Models](https://mlsanity.com/paper/2402.17879/) (2024)
- [Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models](https://mlsanity.com/paper/2502.11881/) (2025)
- [Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning](https://mlsanity.com/paper/2402.17930/) (2024)
- [Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning](https://mlsanity.com/paper/2402.06025/) (2024)
- [Deep Amortized Inference for Probabilistic Programs](https://mlsanity.com/paper/1610.05735/) (2016)
- [NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants](https://mlsanity.com/paper/2301.05223/) (2023)
- [PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception](https://mlsanity.com/paper/2103.01933/) (2021)
- [TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mind](https://mlsanity.com/paper/2407.01455/) (2024)
- [HandMeThat: Human-Robot Communication in Physical and Social Environments](https://mlsanity.com/paper/2310.03779/) (2023)
- [Proactive Robot Assistance via Spatio-Temporal Object Modeling](https://mlsanity.com/paper/2211.15501/) (2022)
- [GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment](https://mlsanity.com/paper/2403.11075/) (2024)
- [A Notion of Complexity for Theory of Mind via Discrete World Models](https://mlsanity.com/paper/2406.11911/) (2024)
- [StylePredict: Machine Theory of Mind for Human Driver Behavior From Trajectories](https://mlsanity.com/paper/2011.04816/) (2020)
- [Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration](https://mlsanity.com/paper/1802.01780/) (2018)
- [Neural Amortized Inference for Nested Multi-agent Reasoning](https://mlsanity.com/paper/2308.11071/) (2023)

## Built on by (most cited first, 23 of 23)

- [Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models](https://mlsanity.com/paper/2507.12547/) (2025)
- [ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind](https://mlsanity.com/paper/2505.22961/) (2025)
- [Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task](https://mlsanity.com/paper/2507.16196/) (2025)
- [Modeling Others' Minds as Code](https://mlsanity.com/paper/2510.01272/) (2025)
- [ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions](https://mlsanity.com/paper/2605.20087/) (2026)
- [AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses](https://mlsanity.com/paper/2608.12307/) (2026)
- [TactfulToM: Do LLMs Have the Theory of Mind Ability to Understand White Lies?](https://mlsanity.com/paper/2509.17054/) (2025)
- [MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents](https://mlsanity.com/paper/2511.23055/) (2025)
- [From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning](https://mlsanity.com/paper/2606.09092/) (2026)
- [BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind](https://mlsanity.com/paper/2505.12321/) (2025)
- [Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language](https://mlsanity.com/paper/2511.15887/) (2025)
- [RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems](https://mlsanity.com/paper/2511.22275/) (2025)
- [A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind](https://mlsanity.com/paper/2511.22536/) (2025)
- [Grounding Social Perception in Intuitive Physics](https://mlsanity.com/paper/2603.27410/) (2026)
- [PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State Tracking](https://mlsanity.com/paper/2604.17819/) (2026)
- [UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind](https://mlsanity.com/paper/2605.27721/) (2026)
- [Hypotheses-Guided Self Distillation for Continual Personalization](https://mlsanity.com/paper/2609.00251/) (2026)
- [Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States](https://mlsanity.com/paper/2609.15972/) (2026)
- [TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence](https://mlsanity.com/paper/2505.24500/) (2025)
- [MindZero: Learning Online Mental Reasoning With Zero Annotations](https://mlsanity.com/paper/2606.00240/) (2026)
- [Resonant Minds: Closed-Loop Social Avatars with Theory of Mind](https://mlsanity.com/paper/2606.05896/) (2026)
- [RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments](https://mlsanity.com/paper/2606.26094/) (2026)
- [OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation](https://mlsanity.com/paper/2609.39727/) (2026)

## Abstract (arXiv)

Theory of Mind (ToM), the ability to understand people's minds based on their behavior, is key to developing socially intelligent agents. Current approaches to ToM reasoning either rely on prompting Large Language Models (LLMs), which are prone to systematic errors, or use handcrafted, rigid agent models for model-based inference, which are more robust but fail to generalize across domains. In this work, we introduce AutoToM, an automated agent modeling method for scalable, robust, and interpretable mental inference. Given a ToM problem, AutoToM first proposes an initial agent model and then performs automated Bayesian inverse planning based on this model, leveraging an LLM backend. Guided by inference uncertainty, it iteratively refines the model by introducing additional mental variables and/or incorporating more timesteps in the context. Across five diverse benchmarks, AutoToM outperforms existing ToM methods and even large reasoning models. Additionally, we show that AutoToM can produce human-like confidence estimates and enable online mental inference for embodied decision-making.