Mental-Models for Multi-Agent Systems
We introduce mental-model-enabled agents, a framework that equips an agent with a latent mental model of its counterpart, allowing it to infer hidden beliefs, intentions, and likely reactions from the observed history and use these inferences to guide action selection.
ProofPaper ↗
Key points
- Large foundation models have accelerated progress toward general-purpose agents that interact with humans and other agents through language and multimodal signals.
- Current agentic systems often operate through prompt design, memory, or end-to-end behavioral shaping, but typically do not learn an explicit partner-state representation that can be reused as a decision variable across tasks.
- Our method learns an amortized recursive Theory-of-Mind representation, with first- and second-order mental-state structure, jointly with a belief-conditioned reward model that evaluates candidate actions relative to the inferred partner state.
- Across these settings, explicit mental-state modeling consistently improves interaction quality and Theory-of-Mind performance over base agentic systems, showing that structured partner modeling is a useful inductive bias for general multi-agent systems.
Sources (1)
- [1]Mental-Models for Multi-Agent SystemsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 05:59 PM
We introduce mental-model-enabled agents, a framework that equips an agent with a latent mental model of its counterpart, allowing it to infer hidden beliefs, intentions, and likely reactions from the observed history and use these inferences to guide action selection.
Large foundation models have accelerated progress toward general-purpose agents that interact with humans and other agents through language and multimodal signals.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
- Oct 7, 2026I would rather quit NLP than read another paper like this: The rise of antithesis in NLP papers
- Oct 7, 2026BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation
- Oct 7, 2026Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
- Oct 7, 2026World Potential Model: Pretrained World Knowledge as Progress Potentials
- Oct 7, 2026Efficient Best-of-N policy evaluation for inference-time alignment
