[2511.04235] Shared Spatial Memory Through Predictive Coding

Computer Science > Artificial Intelligence arXiv:2511.04235 (cs) [Submitted on 6 Nov 2025 (v1), last revised 27 Mar 2026 (this version, v4)] Title:Shared Spatial Memory Through Predictive Coding Authors:Zhengru Fang, Yu Guo, Yuang Zhang, Haonan An, Wenbo Ding, Yuguang Fang View a PDF of the paper titled Shared Spatial Memory Through Predictive Coding, by Zhengru Fang and 4 other authors View PDF HTML (experimental) Abstract:Constructing a consistent shared spatial memory is a critical challenge in multi-agent systems, where partial observability and limited bandwidth often lead to catastrophic failures in coordination. We introduce a multi-agent predictive coding framework that formulates coordination as the minimization of mutual uncertainty among agents. Through an information bottleneck objective, this framework prompts agents to learn not only who and what to communicate but also when. At the foundation of this framework lies a grid-cell-like metric as internal spatial coding for self-localization, emerging spontaneously from self-supervised motion prediction. Building upon this internal spatial code, agents gradually develop a bandwidth-efficient communication mechanism and specialized neural populations that encode partners' locations-an artificial analogue of hippocampal social place cells (SPCs). These social representations are further utilized by a hierarchical reinforcement learning policy that actively explores to reduce joint uncertainty. On the Memory-Maze be...