arXiv：cs.AI· Sen Zhao, Jia Tang, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Ding Zou, Xinyu He, Xu Zhang, Junwei Han·· 7 小时前AI 评分32
TopoPlanner：面向 LLM 智能体的拓扑一致任务规划框架
Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents
AI 导读
研究者提出 TopoPlanner，将工具依赖图提升为 cellular workflow complexes，作为拓扑感知上下文用于 LLM 工具规划，以支持验证-修正循环、分支汇聚和可复用中间状态等流程模式。
正文
Abstract:Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for sequential or directed acyclic graph (DAG)-like structures, they struggle with workflow patterns such as verification-correction loops, convergent branch merging, and reusable intermediate states that arise naturally in real-world tool orchestration. We present TopoPlanner, a topology-consistent planning framework that lifts tool dependency graphs into cellular workflow complexes and uses them as topologyaware context for LLM tool planning. TopoPlanner retrieves a request-relevant closed subcomplex through cosheaf-consistent cellular retrieval, performs multidimensional structural reasoning over the retrieved topology, and interfaces the resulting cellular representation with the planner LLM for tool-sequence generation. Experiments on four tool-planning benchmarks with topology-guided loop, merge, and loop-merge workflows show consistent improvements over prompt-based and graph-enhanced baselines across different local LLM backbones.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07004 [cs.AI] |
| (or arXiv:2610.07004v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07004 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sen Zhao [view email]
[v1]
Sun, 4 Oct 2026 10:24:20 UTC (3,512 KB)
来源：arXiv：cs.AI · arxiv.org