HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents

HyperAgent：面向工具使用型大语言模型智能体的工具模式超图规划与执行

Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains challenging due to the limitations of implicit reasoning and the evolving nature of real-world execution environments. 大语言模型（LLM）智能体正日益依赖外部工具来完成复杂的现实世界任务。然而，由于隐式推理的局限性以及现实执行环境的动态演变，可靠的工具使用规划仍然面临挑战。

Existing tool-use agents typically rely on LLMs to infer tool compositions from textual descriptions, which can lead to inefficient exploration and unreliable execution in complex tasks. To address these challenges, we model tool relations at the schema level and construct a directed Tool-Schema Hypergraph, in which tools are represented as hyperedges from their required input-schema nodes to their output-schema nodes. 现有的工具使用智能体通常依赖大语言模型从文本描述中推断工具组合，这可能导致在复杂任务中出现探索效率低下和执行不可靠的问题。为了应对这些挑战，我们在模式（Schema）层面建模工具关系，并构建了一个有向“工具-模式超图”（Tool-Schema Hypergraph），其中工具被表示为从其所需输入模式节点指向其输出模式节点的超边。

Furthermore, we propose HyperAgent, a Tool-Schema Hypergraph-guided framework for dynamic planning and execution. Given a task, HyperAgent first extracts a task-relevant tool context graph and uses it to guide the construction of a schema-aware Task DAG. 此外，我们提出了 HyperAgent，这是一个由工具-模式超图引导的动态规划与执行框架。给定一个任务，HyperAgent 首先提取与任务相关的工具上下文图，并利用它来指导构建感知模式的任务有向无环图（Task DAG）。

During execution, HyperAgent dynamically realizes each subtask by constructing a state-conditioned tool support graph through deficit-oriented expansion, which identifies unresolved requirements and retrieves supporting producer tools according to the current agent state. 在执行过程中，HyperAgent 通过“面向缺陷的扩展”（deficit-oriented expansion）构建状态条件下的工具支持图，从而动态实现每个子任务。该机制能够识别未解决的需求，并根据当前的智能体状态检索相应的生产者工具。

Experiments on AppWorld demonstrate that HyperAgent improves task completion performance while reducing redundant API calls, LLM interactions, and token consumption compared with existing agent baselines. 在 AppWorld 上的实验表明，与现有的智能体基准相比，HyperAgent 在提升任务完成性能的同时，减少了冗余的 API 调用、大语言模型交互次数以及 Token 消耗。