让多个AI代理协作时自动验证任务交接，提升成功率。
Verification-Aware Planning for Multi-Agent Systems
- 将任务拆解为子任务，用可执行代码和自然语言定义验证规则。
- 在多个数据集上表现优于单/多代理基线，错误率显著降低。
- 无需外部标注，适合需要高可靠性的复杂任务系统。
大型语言模型代理正被用于解决复杂任务，常需多个专业代理协作。但多代理协作带来规划、协调与验证的新挑战。执行失败常源于任务理解偏差、输出格式不一致或代理间交接失误。为此，我们提出VeriMAP框架，实现带有验证意识的多代理协作规划。VeriMAP规划器分解任务，建模子任务依赖关系，并将规划者定义的传递标准编码为子任务验证函数（VFs），以Python和自然语言表示。我们在多种数据集上评估VeriMAP，结果表明其性能优于单代理与多代理基线，同时提升了系统的鲁棒性与可解释性。分析显示，验证意识规划可实现可靠的协同与迭代优化，且无需依赖外部标签或注释。
原文摘要 · Abstract (English)
Large language model (LLM) agents are increasingly deployed to tackle complex tasks, often necessitating collaboration among multiple specialized agents. However, multi-agent collaboration introduces new challenges in planning, coordination, and verification. Execution failures frequently arise not from flawed reasoning alone, but from subtle misalignments in task interpretation, output format, or inter-agent handoffs. To address these challenges, we present VeriMAP, a framework for multi-agent collaboration with verification-aware planning. The VeriMAP planner decomposes tasks, models subtask dependencies, and encodes planner-defined passing criteria as subtask verification functions (VFs) in Python and natural language. We evaluate VeriMAP on diverse datasets, demonstrating that it outperforms both single- and multi-agent baselines while enhancing system robustness and interpretability. Our analysis highlights how verification-aware planning enables reliable coordination and iterative refinement in multi-agent systems, without relying on external labels or annotations.
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。