GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems
2026-02-17 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors address a common problem in systems where multiple agents work together but can only see part of the situation. Existing methods either focus too much on past info or don't use shared communication effectively. They introduce GlobeDiff, a new approach that guesses the overall state by combining different local observations using a special process called multi-modal diffusion. The authors show that their method can predict the global state accurately and prove that its estimation errors are limited. Tests show that GlobeDiff works better than previous methods at figuring out the full picture.
multi-agent systemspartial observabilityglobal state estimationbelief stateinter-agent communicationmulti-modal diffusionstate inferenceestimation error bounds
Authors
Yiqin Yang, Xu Yang, Yuhua Jiang, Ni Mu, Hao Hu, Runpeng Xie, Ziyou Zhang, Siyuan Li, Yuan-Hua Ni, Qianchuan Zhao, Bo Xu
Abstract
In the realm of multi-agent systems, the challenge of \emph{partial observability} is a critical barrier to effective coordination and decision-making. Existing approaches, such as belief state estimation and inter-agent communication, often fall short. Belief-based methods are limited by their focus on past experiences without fully leveraging global information, while communication methods often lack a robust model to effectively utilize the auxiliary information they provide. To solve this issue, we propose Global State Diffusion Algorithm~(GlobeDiff) to infer the global state based on the local observations. By formulating the state inference process as a multi-modal diffusion process, GlobeDiff overcomes ambiguities in state estimation while simultaneously inferring the global state with high fidelity. We prove that the estimation error of GlobeDiff under both unimodal and multi-modal distributions can be bounded. Extensive experimental results demonstrate that GlobeDiff achieves superior performance and is capable of accurately inferring the global state.