CAIRN：用于多智能体探索的动态事实-意图DAG
CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration
浏览论文内容
中文总结 AI 辅助
CAIRN提出事实-意图驱动的多智能体DAG范式，通过动态图协调并行探索，在高努力任务中实现76.5%的加速，最高3.08倍，并降低相对令牌开销。
中文摘要 AI 辅助
基于LLM的自主系统在数学推理、工程和网络安全领域展现了令人瞩目的能力。然而，如何组织这些系统以实现有效、可靠且持续的性能仍然是一个开放问题。在本文中，我们提出了CAIRN，一种面向目标导向探索的事实-意图驱动的多智能体范式。CAIRN将观察结果和计划中的调查表示为动态有向无环图（DAG）。一个推理器解释事实以提出意图，工作器执行这些意图以产生新的事实。每个意图引用其支持的事实并定义一个潜在的探索分支。持久化的图结构跨工作器保留目标、依赖关系和发现，支持知识重用和并行探索。该图还使执行轨迹可追踪和可审计，为人工验证和干预提供基础。我们在网络安全和数学推理任务上评估了CAIRN，考察了任务成功率、解决时间和令牌消耗。基于DAG的协调在低努力任务上可能产生更高的令牌成本，且没有可观察的性能提升。然而，在高努力任务（至少100万令牌）上，我们在76.5%的案例中观察到更快的解决方案，加速比最高达3.08倍。此外，随着任务努力程度的增加，这些时间收益变得更加显著，而相对令牌开销下降，突显了DAG引导的并行探索的潜力。
英文摘要
LLM-powered autonomous systems have demonstrated promising capabilities in mathematical reasoning, engineering, and cybersecurity. Yet how to organize these systems for effective, reliable, and sustained performance remains an open question. In this paper, we present CAIRN, a fact-intent-driven multi-agent paradigm for goal-directed exploration. CAIRN represents observations and planned investigations as a dynamic directed acyclic graph (DAG). A reasoner interprets facts to propose intents, which workers execute to produce new facts. Each intent references its supporting facts and defines a potential exploration branch. The persistent graph preserves goals, dependencies and findings across workers, supporting knowledge reuse and parallel exploration. The graph also makes execution trajectories traceable and auditable, providing a basis for human verification and intervention. We evaluate CAIRN across cybersecurity and mathematical reasoning tasks, examining task success, time to solution, and token consumption. DAG-based coordination can incur higher token costs with no observable performance gains on tasks that require little effort. However, on high-effort tasks (at least 1M tokens), we observe faster solutions in 76.5% of cases, with speedups of up to 3.08x. Moreover, as task effort increases, these time gains become more pronounced while relative token overhead declines, highlighting the potential of DAG-guided parallel exploration.
