给大模型协作系统加入关系预期，能促进共识但未必更准确。
Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems
- 用自然语言显式设定代理间关系，作为协调压力源。
- 关系正向性越高，协作与一致越强，尤其在资源治理中有效。
- 适用于需共识的任务，但需验证是否提升正确性，避免盲目使用。
基于大语言模型的多智能体系统（LLM-MAS）通过角色设定、辩论协议和聚合规则构建，隐含社会期待：代理可能被期望信任、质疑、服从或合作。本文研究将代理间关系语义显式化的影响。采用最小化的有符号网络形式表示关系先验，并将自然语言描述注入系统提示，保持任务协议不变。在公共资源治理模拟与多智能体辩论中，关系先验主要表现为收敛压力：关系正向性越强，代理越易达成协调或一致。该压力在奖励行为一致性的任务中（如可持续资源治理、主观共识）有益，但无法可靠提升准确性。在客观问答辩论中，更高正向性可能增加一致性，但正确性相关的共识并未提升，甚至下降。效果受模型基座、关系类型和拓扑结构影响；显式中立不等于无关系框架。我们主张关系先验不应作为默认组件。其安全使用应为诊断性且任务特定：对比无先验基线，当真相重要时监控正确性相关指标，若验证不支持则应移除关系层。
原文摘要 · Abstract (English)
Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create implicit social expectations: agents may be expected to trust, challenge, defer to, or collaborate with peers. We study the effects of making inter-agent relation semantics explicit. We use a minimal signed-network formulation of relational priors and inject natural-language renderings into agent system prompts while holding the task protocol fixed. Across a commons-governance simulation and multi-agent debate, relational priors primarily act as convergence pressure: increasing relational positivity tends to make agents coordinate or agree more readily. This pressure can help when utility rewards behavioral alignment, as in sustainable resource governance and subjective consensus. It does not, however, reliably improve accuracy. In objective QA debates, higher positivity can increase agreement even when correctness-conditioned agreement does not improve and may decline in some settings. Effects vary by model backbone, relation type, and topology; explicit neutrality is not equivalent to omitting relational framing. We argue that relational priors should not be a default add-on for LLM-MAS. Their safer use is diagnostic and task-specific: compare against a no-prior baseline, monitor correctness-conditioned metrics when truth matters, and omit the relational layer when validation does not justify it.
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。