arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.20184cs.DC
收藏

使推理LLM代理达成一致

Reaching Agreement Among Reasoning LLM Agents

NUS(新加坡国立大学)

Chaoyi Ruan, Yiliang Wang, Ziji Shi, Jialin Li

AI总结:

Aegean通过引入基于共识的协议,为多代理推理提供正式模型,有效减少延迟并保持答案质量。

摘要:

多代理系统已经扩展了代理AI的能力。与其使用单次推理过程,多个代理进行集体推理以推导高质量答案。然而,现有的多代理协调依赖于静态启发式工作流,如固定的循环限制和屏障同步。这些随意的方法浪费计算资源,由于慢节点导致延迟高,并且可能最终达成暂时的一致。我们认为可靠的多代理推理需要类似于经典分布式共识问题的正式基础。为此,我们提出一个多代理细化问题的正式模型。该模型包括正确性保证和代理推理的正式语义的定义。然后我们引入Aegean,一种为随机推理代理设计的共识协议,用于解决多代理细化问题。我们将在Aegean-Serve中实现该协议,这是一种具有共识意识的服务引擎,它在并发代理执行中执行增量多数检测,当足够多的代理收敛时能够实现早期终止。使用四个数学推理基准测试的评估显示,Aegean提供了可证明的安全性和活锁保证,同时将延迟降低了1.2-20倍,与最先进的基线相比,保持答案质量在2.5%以内。在本地GPU部署和商业API提供商上的一致收益验证了基于共识的协调消除了慢节点延迟而不牺牲正确性。

英文摘要:

Multi-agent systems have extended the capability of agentic AI. Instead of single inference passes, multiple agents perform collective reasoning to derive high quality answers. However, existing multi-agent orchestration relies on static heuristic workflows such as fixed loop limits and barrier synchronization. These ad-hoc approaches waste computational resources, incur high latency due to stragglers, and risk finalizing transient agreements. We argue that reliable multi-agent reasoning requires a formal foundation analogous to classical distributed consensus problem. To that end, we propose a formal model of the multi-agent refinement problem. The model includes definitions of the correctness guarantees and formal semantics of agent reasoning. We then introduce Aegean, a consensus protocol designed for stochastic reasoning agents that solves multi-agent refinement. We implement the protocol in Aegean-Serve, a consensus-aware serving engine that performs incremental quorum detection across concurrent agent executions, enabling early termination when sufficient agents converge. Evaluation using four mathematical reasoning benchmarks shows that Aegean provides provable safety and liveness guarantees while reducing latency by 1.2--20$\times$ compared to state-of-the-art baselines, maintaining answer quality within 2.5%. Consistent gains across both local GPU deployments and commercial API providers validate that consensus-based orchestration eliminates straggler delays without sacrificing correctness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑