通过量化角色清晰度提升大模型多智能体协作中的角色一致性
Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity
- 构建角色相似度矩阵，用数学方式衡量角色描述与行为的匹配程度
- 使用角色清晰度作为正则项，使智能体更严格遵守自身角色，角色越界率降至不足1%
- 适合研究多智能体系统、角色分工与协作机制的开发者和研究人员
在大语言模型驱动的多智能体系统中，偏离角色设定（即不遵守分配职责和约束，导致行为与其他角色混淆）是主要故障模式。本文提出一种量化角色清晰度的方法来提升角色一致性。首先构建角色分配矩阵 $S(ϕ)=[s_{ij}(ϕ)]$，其中 $s_{ij}(ϕ)$ 表示第 $i$ 个智能体的行为轨迹与第 $j$ 个角色描述之间的语义相似度。随后定义角色清晰度矩阵 $M(ϕ) = \text{softmax}(S(ϕ)) - I$，其中 $\text{softmax}(S(ϕ))$ 是 $S(ϕ)$ 的行方向 softmax，$I$ 为单位矩阵。$M(ϕ)$ 的 Frobenius 范数用于量化角色描述与行为轨迹之间的对齐程度。进一步地，将角色清晰度矩阵作为正则项用于轻量级微调，以增强角色一致性，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，该方法显著提升了角色一致性和任务表现：使用 Qwen 和 Llama 时，角色越界率分别从 46.4% 降至 8.4% 和从 43.4% 降至 0.2%，角色清晰度得分分别从 0.5328 提升至 0.9097 和从 0.5007 提升至 0.8530，任务成功率分别从 0.6769 提升至 0.6909 和从 0.6174 提升至 0.6763。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。