让大模型代理通过心理特质推断提升协作效率
Explicit Trait Inference for Multi-Agent Coordination
- 基于心理维度推断伙伴的亲和与能力特质
- 经济博弈中减少45%-77%收益损失，复杂场景提效3%-29%
- 适合需要稳定协作的大模型多智能体系统
基于大语言模型的多智能体系统在复杂任务中表现良好，但易出现目标偏离、错误传递和行为不一致等问题。本文提出显式特质推断（ETI），一种基于心理学理论的方法，使智能体能从交互历史中推断并追踪伙伴在‘亲和性’（如信任）和‘能力’（如技能）两个心理维度上的特征，以指导决策。在受控环境（经济博弈）中，ETI将收益损失降低45%-77%；在更真实的复杂多智能体设置（MultiAgentBench）中，相对于思维链（CoT）基线，性能提升3%-29%，具体取决于场景和模型。进一步分析表明，性能提升与特质推断紧密相关：ETI生成的特质画像能有效预测智能体行为，且信息量丰富的画像驱动改进。结果表明，ETI是一种轻量且鲁棒的协作增强机制，并首次系统证明大语言模型智能体可（i）可靠地从交互历史中推断他人特质，（ii）利用对他人特质的结构化认知实现高效协作。
原文摘要 · Abstract (English)
LLM-based multi-agent systems (MAS) show promise on complex tasks but remain prone to coordination failures such as goal drift, error cascades, and misaligned behaviors. We propose Explicit Trait Inference (ETI), a psychologically grounded method for improving coordination. ETI enables agents to infer and track partner characteristics along two established psychological dimensions--warmth (e.g., trust) and competence (e.g., skill)--from interaction histories to guide decisions. We evaluate ETI in controlled settings (economic games), where it reduces payoff loss by 45-77%, and in more realistic, complex multi-agent settings (MultiAgentBench), where it improves performance by 3-29% depending on the scenario and model, relative to a CoT baseline. Additional analysis shows that gains are closely linked to trait inference: ETI profiles predict agents' actions, and informative profiles drive improvements. These results highlight ETI as a lightweight and robust mechanism for improving coordination in diverse multi-agent settings, and provide the first systematic evidence that LLM agents can (i) reliably infer others' traits from interaction histories and (ii) leverage structured awareness of others' traits for coordination.
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。