让大模型代理在企业中长期稳定运作，靠的是记忆驱动的协调机制。
Can LLM Agents Sustain Long-Horizon Organizational Dynamics?
- 用四步循环维持计划状态，依赖记忆追踪任务执行
- 一年模拟中保持组织一致性，产出可落地的成果
- 适合想构建真实企业级大模型系统的开发者
大语言模型代理被越来越多用于社会模拟，但其在结构化组织中是否能持续保持连贯行为仍不明确。组织需目标逐层传递、任务依赖前置执行、成果长期积累。本文将长周期组织模拟视为以记忆为中心的协调问题，提出层级式代理框架 TaskWeave，通过「制定-拆分-诊断-对齐」循环维持规划状态，并利用依赖感知的追踪记忆实现执行落地。我们在一年期的IT公司模拟中评估 TaskWeave，对比其他多代理框架在组织连贯性、执行接地性和下游企业NLP应用价值上的表现。实验表明，TaskWeave 能支持连贯的长期组织动态，生成可落地的成果，并适应外部环境变化。结果表明，结构化模拟记忆是构建可靠大模型组织模拟器的关键机制。
原文摘要 · Abstract (English)
Large language agents are increasingly used for social simulation, yet it remains unclear whether they can sustain coherent behavior in structured organizations, where goals must propagate through hierarchy, tasks depend on prior execution, and artifacts accumulate over long horizons. We formulate long-horizon organizational simulation as a memory-centered coordination problem and introduce TaskWeave, a hierarchical agentic framework that maintains planning states through a Formulate-Partition-Diagnose-Align cycle and grounds execution through dependency-aware trace memory. We evaluate TaskWeave in a year-long IT company simulation and compare it with other multi-agent frameworks on organizational coherence, execution grounding, and downstream enterprise NLP utility. Experiments show that TaskWeave supports coherent and long-horizon organizational dynamics while producing grounded artifacts and adapting to external environments. These findings suggest that structured simulation memory is a key mechanism for building reliable LLM-based organizational simulators.
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。