---
title: "From Traits to Roles: Consensus-Guided Composition of Orthogonal Experts for Cooperative MARL"
authors:
  - "Yewei Zhou"
  - "Bin Zhang"
  - "Ying Zhou"
  - "Xuri Ge"
  - "Dapeng Li"
  - "Hangyu Mao"
  - "Pengjie Ren"
  - "Zhiwei Xu"
doi: "10.24963/ijcai.2026/55"
url: "https://ijcai.org/proceedings/2026/55"
pdf: "https://ijcai.org/proceedings/2026/0055.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "481-489"
track: "Main Track"
keywords:
  - "Agent-based and Multi-agent Systems: Multi-agent learning"
---

# From Traits to Roles: Consensus-Guided Composition of Orthogonal Experts for Cooperative MARL

Yewei Zhou, Bin Zhang, Ying Zhou, Xuri Ge, Dapeng Li, Hangyu Mao, Pengjie Ren, Zhiwei Xu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 481-489. DOI: [10.24963/ijcai.2026/55](https://doi.org/10.24963/ijcai.2026/55)

## Abstract

Parameter sharing is a central design choice in cooperative multi-agent reinforcement learning, yet it fundamentally conflicts with the need for role specialization in heterogeneous cooperative environments. Existing role-based methods typically learn monolithic role representations, which often suffer from gradient interference and fail to capture the compositional structure of complex behaviors. Inspired by Trait Theory, we propose DEcompose and COnstruct Roles (DECOR), a framework that models agent roles as dynamic compositions of orthogonal behavioral traits. DECOR introduces an orthogonal Mixture-of-Experts architecture to decompose behaviors into independent traits, mitigating destructive gradient interference under parameter sharing, and a group-consensus guided mechanism to extract team-level tactical intents that guide role composition.Experiments on multiple benchmarks demonstrate that DECOR consistently improves sample efficiency and overall performance over existing related methods.