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
Die Bildung eines token-spezifischen Agent-Theorie-of-Mind (ToM) ist der Schlüssel zu einer erfolgreichen Multi-Agent-Kollaboration und erfordert Argumentation unter Unsicherheit, um mehrere mögliche Partner-Staaten zu erfassen. Dies ist schwierig in der Text-Repräsentation-Raum native zu großen Sprachmodell (LLM) Agenten, die leichter beschreiben einen einzigen Partner-Status. Um diese Herausforderung zu lösen, führen wir ToM2Vec, die lernt, abstrakte Theorien-of-Mind in einem reichen latenten Raum durch einen festen Budget der kontinuierlichen Argumentation-Token zu bilden. Während des Trainings, die Aufsicht für diese Token kommt von den tatsächlichen Gedanken des Partners, die die ToM-Token sind
Machine translation (Meta M2M100); the English original follows.
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
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange