AI 中文总结
研究基于LLM的多智能体实体规划执行延迟高问题，提出Mosaic框架，通过智能体中心语义内存和整数线性规划应对挑战，在多基准测试中执行更快、调用更少、步数更少且成功率更高，证明相关因素对多智能体规划的重要性。
AI 中文摘要
基于大语言模型（LLM）的多智能体实体规划因执行延迟过高而不实用。我们将失败的行动识别为主要瓶颈，其源于部分可观测性下不准确的状态跟踪和产生冗余或冲突行动的低效协调这两个核心挑战。我们引入了Mosaic，一个运行时高效的多智能体规划框架来应对这两个挑战。Mosaic通过以智能体为中心的语义内存维持准确且轻量级的状态跟踪，通过整数线性规划确保高效协调。在AI2-THOR和搜索救援基准测试中，Mosaic执行速度快27 - 32%，LLM调用少30 - 33%，步数少25 - 31%，成功率高4 - 10个百分点。这些结果表明高效内存和约束引导协调对可扩展、低延迟多智能体规划至关重要。
英文摘要
LLM-based multi-agent embodied planning remains impractical due to prohibitively high execution latency. We identify failed actions as the dominant bottleneck, stemming from two core challenges: inaccurate state tracking under partial observability and inefficient coordination that produces redundant or conflicting actions. We introduce Mosaic, a runtime-efficient multi-agent planning framework that addresses both challenges. Mosaic maintains accurate yet lightweight state tracking through agent-centric semantic memory that stores objects in relative coordinates, enabling geometric transformations and coordination. It ensures efficient coordination through Integer Linear Programming that allocates actions at every planning step, enforcing physical feasibility and inter-agent coordination constraints. Across AI2-THOR and search-and-rescue benchmarks, Mosaic achieves 27-32% faster execution, 30-33% fewer LLM calls, 25-31% fewer steps, and 4-10% points higher success rates. These results demonstrate that efficient memory and constraint-guided coordination are critical for scalable, low-latency multi-agent planning.
CommentsAccepted to ICML 2026
