发表机构
Nanjing University; School of Artificial Intelligence, Nanjing University（南京大学; 南京大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TaReD是一种工具感知递归分解方法，通过将工具组织为能力层次结构，按需分解长程任务，使复杂现实任务的端到端成功率较基线最高提升40个百分点。
AI 中文摘要
智能体将推理与工具结合，以与外部系统交互并完成现实世界任务。早期智能体通常沿单一执行链交替进行推理与动作，在复杂任务中，该链因不断增长的历史会掩盖中间依赖关系，且使早期规划错误得以传播，变得不可靠。将复杂任务递归分解为更小的子任务是自然的解决方案，但有效分解必须考虑系统能力，确保每个子任务可由可用工具执行。然而在现实系统中，工具库可能过大而无法完整暴露，注入所有工具描述会消耗大量上下文，同时使相关工具更难检索、有用任务边界更难识别。我们提出工具感知递归分解，该方法按功能关系将工具组织为能力层次结构；执行期间，智能体按需发现工具，并利用该层次结构将复杂任务递归分解为子任务树，其层级与各阶段所需能力对齐。在复杂现实世界任务上的实验表明，所提方法的端到端任务成功率相比对比基线最高提升40个百分点。TaReD的实现可在GitHub获取：this https URL。
英文摘要
Agents combine reasoning with tools to interact with external systems and complete real-world tasks. Early agents typically interleave reasoning and actions along a single execution chain. On complex tasks, this chain becomes unreliable because growing histories obscure intermediate dependencies and allow early planning errors to propagate. Recursively decomposing a complex task into smaller subtasks offers a natural solution, yet effective decomposition must account for the system's capabilities so that each subtask can be executed by the available tools. In realistic systems, however, tool libraries can be too large to expose in full. Injecting every tool description consumes substantial context while making relevant tools harder to retrieve and useful task boundaries harder to identify. We propose tool-aware recursive decomposition, which organizes tools by functional relationships into a hierarchy of capabilities. During execution, the agent discovers tools on demand and uses the hierarchy to recursively decompose a complex task into a subtask tree whose levels are aligned with the capabilities required at each stage. Experiments on complex real-world tasks show that the proposed method improves end-to-end task success rate by up to 40 percentage points over the compared baselines. The implementation of TaReD is available on GitHub: https://github.com/WeiXiang-Mao/TaReD.
Comments15 pages, 3 figures, 2 tables
