mlsanityData to 7 Oct 2026

BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind

arXiv 2505.12321 ↗First posted 18 May 2025cs.AIcited by 1

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

This paper introduces an open-source simulator, BeliefNest, designed to enable embodied agents to perform collaborative tasks by leveraging Theory of Mind. BeliefNest dynamically and hierarchically constructs simulators within a Minecraft environment, allowing agents to explicitly represent nested belief states about themselves and others. This enables agent control in open-domain tasks that require Theory of Mind reasoning. The simulator provides a prompt generation mechanism based on each belief state, facilitating the design and evaluation of methods for agent control utilizing large language models (LLMs). We demonstrate through experiments that agents can infer others' beliefs and predict their belief-based actions in false-belief tasks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 28 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

17 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Models25 May

Other references · 16

  1. 2024GPT-4o System Cardcited by 4,467
  2. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  3. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 231
  4. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  5. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 217
  6. 2023Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilitiescited by 86
  7. 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoningcited by 65
  8. 2024LLMs achieve adult human performance on higher-order theory of mind taskscited by 59
  9. 2024OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Modelscited by 54
  10. 2024Project Sid: Many-agent simulations toward AI civilizationcited by 46
  11. 2025AutoToM: Scaling Model-based Mental Inference via Automated Agent Modelingcited by 23
  12. 2023Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learningcited by 19
4 more
  1. 2024GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignmentcited by 16
  2. 2021Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Beliefcited by 7
  3. 2025ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignmentcited by 6
  4. 2023An Explainable Collaborative Dialogue System using a Theory of Mindcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47

Similar, not cited

Close in wording, no citation either way

  1. 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
  2. 2024MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
  3. 2026Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
  4. 2024MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control
  5. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
  6. 2026Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models
  7. 2025MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents
  8. 2024ADAM: An Embodied Causal Agent in Open-World Environments