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

DOI: 10.48550/arXiv.2610.29934 · open-access PDF

Portuguese

Formar uma teoria-de-mente (ToM) precisa é a chave para uma colaboração multi-agente bem-sucedida e requer raciocínio sob incerteza para capturar múltiplos estados de parceiros possíveis. Isto é difícil de fazer no espaço de representação de texto nativo a grande modelo de linguagem (LLM) agentes, que descrevem mais facilmente um único estado de parceiro. Para enfrentar este desafio, apresentamos o ToM2Vec, que aprende a formar teorias abstratas-de-mente em um rico espaço latente através de um orçamento fixo de tokens de raciocínio contínuo. Durante o treinamento, a supervisão desses tokens vem dos pensamentos reais do parceiro, que os tokens ToM

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

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29934, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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