← Back to all news
arXiv AI By Jinnyeong Yang, Yuhwan Jeong, Hoyong Kwon, Minseok Kim, Jihun Kim, Kuk-Jin Yoon

Partially Observable Zero-shot coordination by Predicting Intention of Partner

Read the original on arXiv AI →

The paper introduces Predicting Intention of Partner (PIP), a method for zero‑shot coordination in partially observable settings. PIP employs a Joint‑view VAE to create a partner representation from local observations and uses Partner‑State Belief networks to infer hidden partner states from interaction history. Experiments on Burrito‑PO, Overcooked‑PO, and Melting Pot, along with human evaluation, show that PIP outperforms other methods and demonstrates effective coordination with unseen partners under occlusion.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 9

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

The paper introduces Multi-agent Egocentric World Model (ME-World), a framework that generates synchronized first-person video streams for multiple agents interacting in a shared environment. It addresses fine-grained embodied actions by ensuring cross-view action consistency, shared-environment consistency, and consistent state updates across agents. Experiments on real and synthetic data demonstrate that ME-World outperforms existing methods in shared-world consistency, action control, identity preservation, and video quality.

By Dahyun Chung, Siyoon Jin, Hyunwook Choi, Honggyu An, Junyoung Seo, Hyunsung Kim, Seung Wook Kim, Seungryong Kim
agentsrobotics
More like this →
arXiv AI
Aug 24

Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models

The paper introduces MOSAIC, a benchmark that tests how vision‑language models translate theory‑of‑mind (ToM) reasoning into coordinated social actions across verbal and nonverbal channels. Across 200 trials per model, 13 models—including 11 VLMs—failed to align their behaviors with ToM constraints, revealing bottlenecks in generating coherent nonverbal signals and interpreting others’ actions. A structured model with an explicit ToM module, PCM‑LLM, succeeded in all conditions, indicating that belief‑action coupling is crucial for these tasks.

By Tonglin Yan, Gregoire Sergeant-Perthuis, David Rudrauf
llmsagentsroboticsmultimodalbenchmarks
More like this →