← Search

Zhuohui Zhang

2 accepted papers

2026

DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision Making

ICML 2026spotlight

Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that limit generalization. In contrast, large language models (LL…

Cited by 0SourceScholar
2025

Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems

AAAI 2025technical

Multi-agent systems must learn to communicate and understand interactions between agents to achieve cooperative goals in partially observed tasks. However, existing approaches lack a dynamic directed communication mechanism and rely on global states, thus diminishing the role of communication in cen…