跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-21AI 評分38

ToM2Vec:用於多智能體協作的連續心智理論 token

ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination

AI 導讀

ToM2Vec 透過連續潛在推理 token 學習抽象的夥伴狀態表徵,提升多智能體在不同情境中的協作表現。研究在合作、競爭及混合動機環境中評估,結果顯示其表現持續優於基礎模型及多種具競爭力的訓練和提示基線,並可泛化至訓練時未見的模型系列,包括專有模型 GPT-5.4。

正文

Published on Oct 21

Authors:

,

,

,

Abstract

ToM2Vec learns abstract partner-state representations via continuous latent reasoning tokens to improve multi-agent collaboration across diverse settings.

Forming an accurate theory-of-mind (ToM) is key to successful multi-agent collaboration and requires reasoning under uncertainty to capture multiple possible partner states. This is hard to do in the text representation space native to large language model (LLM) agents, which more easily describe a single partner state. To address this challenge, we introduce ToM2Vec, which learns to form abstract theories-of-mind in a rich latent space via a fixed budget of continuous reasoning tokens. During training, supervision for these tokens comes from the partner's actual thoughts, which the ToM tokens are trained to abstract and match. At test-time, ToM tokens are generated by each agent and act as conditioners for that agent's thoughts and actions. Across several environments covering collaborative, competitive, and mixed-motive settings (Overcooked-AI, multiparty negotiation, Decrypto, Hanabi, and Collab Escape/Capture), we evaluate ToM2Vec's ability to support multi-agent interactions and collaboration, finding consistent improvements over the base model and a variety of competitive trained and prompted baselines. We show that latent reasoning is critical, with performance dropping when reasoning is expressed in text. Moreover, we show that ToM2Vec training generalizes to partner model families not seen at train-time, including a proprietary model (GPT-5.4). In our analysis, we provide evidence that the latent tokens encode a ToM, rather than task-specific information: ToM2Vec's tokens improve the agent's ability to directly answer questions about partner beliefs, desires, and next actions.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.29934

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.29934 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.29934 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.29934 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co