Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.02770 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908934695026688 |
|---|---|
| author | Zhou, Guoling Han, Wenpei Yang, Fengqin Wang, Li Zhou, Yingcong Fu, Zhiguo |
| author_facet | Zhou, Guoling Han, Wenpei Yang, Fengqin Wang, Li Zhou, Yingcong Fu, Zhiguo |
| contents | In large language model (LLM)-driven multi-agent systems, disobey role specification (failure to adhere to the defined responsibilities and constraints of an assigned role, potentially leading to an agent behaving like another) is a major failure mode \cite{DBLP:journals/corr/abs-2503-13657}. To address this issue, in the present paper, we propose a quantitative role clarity to improve role consistency. Firstly, we construct a role assignment matrix $S(ϕ)=[s_{ij}(ϕ)]$, where $s_{ij}(ϕ)$ is the semantic similarity between the $i$-th agent's behavior trajectory and the $j$-th agent's role description. Then we define role clarity matrix $M(ϕ)$ as $\text{softmax}(S(ϕ))-I$, where $\text{softmax}(S(ϕ))$ is a row-wise softmax of $S(ϕ)$ and $I$ is the identity matrix. The Frobenius norm of $M(ϕ)$ quantifies the alignment between agents' role descriptions and their behaviors trajectory. Moreover, we employ the role clarity matrix as a regularizer during lightweight fine-tuning to improve role consistency, thereby improving end-to-end task performance. Experiments on the ChatDev multi-agent system show that our method substantially improves role consistency and task performance: with Qwen and Llama, the role overstepping rate decreases from $46.4\%$ to $8.4\%$ and from $43.4\%$ to $0.2\%$, respectively, and the role clarity score increases from $0.5328$ to $0.9097$ and from $0.5007$ to $0.8530$, respectively, the task success rate increases from $0.6769$ to $0.6909$ and from $0.6174$ to $0.6763$, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02770 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity Zhou, Guoling Han, Wenpei Yang, Fengqin Wang, Li Zhou, Yingcong Fu, Zhiguo Artificial Intelligence In large language model (LLM)-driven multi-agent systems, disobey role specification (failure to adhere to the defined responsibilities and constraints of an assigned role, potentially leading to an agent behaving like another) is a major failure mode \cite{DBLP:journals/corr/abs-2503-13657}. To address this issue, in the present paper, we propose a quantitative role clarity to improve role consistency. Firstly, we construct a role assignment matrix $S(ϕ)=[s_{ij}(ϕ)]$, where $s_{ij}(ϕ)$ is the semantic similarity between the $i$-th agent's behavior trajectory and the $j$-th agent's role description. Then we define role clarity matrix $M(ϕ)$ as $\text{softmax}(S(ϕ))-I$, where $\text{softmax}(S(ϕ))$ is a row-wise softmax of $S(ϕ)$ and $I$ is the identity matrix. The Frobenius norm of $M(ϕ)$ quantifies the alignment between agents' role descriptions and their behaviors trajectory. Moreover, we employ the role clarity matrix as a regularizer during lightweight fine-tuning to improve role consistency, thereby improving end-to-end task performance. Experiments on the ChatDev multi-agent system show that our method substantially improves role consistency and task performance: with Qwen and Llama, the role overstepping rate decreases from $46.4\%$ to $8.4\%$ and from $43.4\%$ to $0.2\%$, respectively, and the role clarity score increases from $0.5328$ to $0.9097$ and from $0.5007$ to $0.8530$, respectively, the task success rate increases from $0.6769$ to $0.6909$ and from $0.6174$ to $0.6763$, respectively. |
| title | Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.02770 |