mlsanityData to 7 Oct 2026

ToMCAT: Theory-of-Mind for Cooperative Agents in Teams via Multiagent Diffusion Policies

arXiv 2502.18438 ↗First posted 25 Feb 2025cs.MA cs.AI cs.LGcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

In this paper we present ToMCAT (Theory-of-Mind for Cooperative Agents in Teams), a new framework for generating ToM-conditioned trajectories. It combines a meta-learning mechanism, that performs ToM reasoning over teammates' underlying goals and future behavior, with a multiagent denoising-diffusion model, that generates plans for an agent and its teammates conditioned on both the agent's goals and its teammates' characteristics, as computed via ToM. We implemented an online planning system that dynamically samples new trajectories (replans) from the diffusion model whenever it detects a divergence between a previously generated plan and the current state of the world. We conducted several experiments using ToMCAT in a simulated cooking domain. Our results highlight the importance of the dynamic replanning mechanism in reducing the usage of resources without sacrificing team performance. We also show that recent observations about the world and teammates' behavior collected by an agent over the course of an episode combined with ToM inferences are crucial to generate team-aware plans for dynamic adaptation to teammates, especially when no prior information is provided about them.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 15 of its 31 references that are in the map. First posted on arXiv 25 Feb 2025.

Builds on

15 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023MADiff: Offline Multi-agent Learning with Diffusion Models27 May
  2. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov

Other references · 13

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  6. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  7. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  8. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
  9. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  10. 2018Machine Theory of Mindcited by 222
  11. 2020Open Problems in Cooperative AIcited by 167
  12. 2017QMDP-Net: Deep Learning for Planning under Partial Observabilitycited by 51
1 more
  1. 2023Multiagent Inverse Reinforcement Learning via Theory of Mind Reasoningcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork
  2. 2026Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning
  3. 2026Adaptive Theory of Mind for LLM-based Multi-Agent Coordination
  4. 2026RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planning
  5. 2025Theory of Mind in Action: The Instruction Inference Task in Dynamic Human-Agent Collaboration
  6. 2026MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization
  7. 2023Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork
  8. 2022Knowledge-based and Data-driven Reasoning and Learning for Ad Hoc Teamwork