构建可追溯的多智能体系统，让错误责任清晰可查。
Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines
- 设计角色分明的规划-执行-评审流水线，每步留痕可追踪。
- 引入结构化交接后，准确率显著提升，错误传播大幅减少。
- 不同模型在各角色表现差异明显，适合按任务特性搭配使用。
基于大语言模型的顺序多智能体系统可自动化复杂软件任务，但因错误在各阶段悄然传递而难以信赖。本文研究一种可追溯且可问责的流水线：明确角色分工、规范任务交接，并保存完整记录，以便追溯每一步操作并定位责任。实验采用规划者→执行者→评审者三阶段架构，在三个基准上测试了三种先进LLM的八种配置，分析错误起源、传播路径及修复方式。结果表明：（1）引入结构化、可问责的任务交接能显著提升准确率，有效防止简单流水线中的常见故障；（2）不同模型在角色中展现明确的能力与风险（如规划稳定但评审波动大），可通过修复率与伤害率量化评估；（3）准确率-成本-延迟权衡取决于任务类型，异构配置通常更高效。本文提供了一套实用、数据驱动的方法，用于设计、追踪和调试可靠、可预测且可问责的多智能体系统。
原文摘要 · Abstract (English)
Sequential multi-agent systems built with large language models (LLMs) can automate complex software tasks, but they are hard to trust because errors quietly pass from one stage to the next. We study a traceable and accountable pipeline, meaning a system with clear roles, structured handoffs, and saved records that let us trace who did what at each step and assign blame when things go wrong. Our setting is a Planner -> Executor -> Critic pipeline. We evaluate eight configurations of three state-of-the-art LLMs on three benchmarks and analyze where errors start, how they spread, and how they can be fixed. Our results show: (1) adding a structured, accountable handoff between agents markedly improves accuracy and prevents the failures common in simple pipelines; (2) models have clear role-specific strengths and risks (e.g., steady planning vs. high-variance critiquing), which we quantify with repair and harm rates; and (3) accuracy-cost-latency trade-offs are task-dependent, with heterogeneous pipelines often the most efficient. Overall, we provide a practical, data-driven method for designing, tracing, and debugging reliable, predictable, and accountable multi-agent systems.
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。