arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.02770cs.AI
收藏

通过量化角色清晰度提升多智能体协作中的角色一致性

Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity

Guoling Zhou, Wenpei Han, Fengqin Yang, Li Wang, Yingcong Zhou, Zhiguo Fu

AI总结:

本文提出量化角色清晰度以提升多智能体协作中的角色一致性,通过构建角色分配矩阵和角色清晰度矩阵,利用Frobenius范数量化角色描述与行为轨迹的一致性,并在轻量微调中作为正则化项提升任务性能。

摘要:

在大型语言模型(LLM)驱动的多智能体系统中,违反角色规范(未能遵守分配角色的定义责任和约束,可能导致智能体行为类似其他智能体)是主要的失败模式。为解决这一问题,本文提出量化角色清晰度以提高角色一致性。首先,我们构建了一个角色分配矩阵S(ϕ)=[s_ij(ϕ)],其中s_ij(ϕ)是第i个智能体的行为轨迹与第j个智能体的角色描述之间的语义相似性。然后我们定义角色清晰度矩阵M(ϕ)为softmax(S(ϕ))-I,其中softmax(S(ϕ))是S(ϕ)的行softmax,I是单位矩阵。M(ϕ)的Frobenius范数量化了智能体角色描述与其行为轨迹之间的一致性。此外,我们利用角色清晰度矩阵在轻量微调中作为正则化项,以提高角色一致性,从而提升端到端任务性能。在ChatDev多智能体系统上的实验表明,我们的方法显著提高了角色一致性和任务性能:使用Qwen和Llama时,角色越界率从46.4%降至8.4%,从43.4%降至0.2%;角色清晰度得分从0.5328升至0.9097,从0.5007升至0.8530;任务成功率从0.6769升至0.6909,从0.6174升至0.6763。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑