Newest papers

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

Nithin Sivakumaran, Ali Payani, Hyunji Lee, Mohit Bansal, Elias Stengel-Eskin · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29934 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Формирование токовой теории мышления агента (ToM) является ключом к успешному многоагентному сотрудничеству и требует рассуждения в условиях неопределенности, чтобы захватить несколько возможных партнерских государств. Это трудно сделать в текстовом пространстве представления родных до больших языковых моделей (LLM) агентов, которые более легко описывают одностороннее партнерское состояние. Чтобы решить эту задачу, мы вводим ToM2Vec, который учится формировать абстрактные теории мышления каждого агента в богатом латентном пространстве через фиксированный бюджет последних токенов непрерывного рассуждения. Во время обучения надзор за этими токенами происходит от фактических мыслей партнера, которые токены ToM обучаются абстрактному и соответствию. В

Machine translation (Meta M2M100); the English original follows.

Abstract

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, ENCODE, Representation (politics), Variety (cybernetics), Space (punctuation), Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange