对数据任务，先规划再执行比一步步试更省资源且效果相当。
Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling
- 用完整计划+按需重规划，替代逐步试探
- 在多种复杂度下准确率与逐步执行相当，耗能减少2-3倍
- 适合追求效率的复杂数据查询场景
显式规划是大模型代理解决复杂数据任务的关键能力，需精准调用外部数据源工具。现有策略基于规划视野分为两类：(1) 全视野（FH）——执行前生成完整计划；(2) 单步视野（SH）——每一步行动后进行增量推理与观察。尽管通常认为逐步执行需实时监控以增强适应性，我们重新审视了这一假设，针对定义清晰的数据任务进行了受控实验，将规划视野作为核心变量，系统分析拓扑复杂度与工具鲁棒性对两种范式的影响。在知识库问答与多跳问答任务中，全视野规划配合懒惰重规划在不同深度、广度和鲁棒性水平下均达到与单步视野相当的准确率，同时减少2-3倍的令牌消耗。结果表明，对于定义清晰的数据任务，无需频繁逐步监控，全视野规划加按需重规划可作为更高效的默认方案。
原文摘要 · Abstract (English)
Explicit planning is a critical capability for LLM-based agents solving complex data-centric tasks, which require precise tool calling over external data sources. Existing strategies fall into two paradigms based on planning horizon: (1) full-horizon (FH), which generates a complete plan before execution, and (2) single-step horizon (SH), which interleaves each action (tool call) with incremental reasoning and observation. While step-by-step execution is a common default under the assumption that eager execution monitoring is necessary for adaptability, we revisit this assumption for well-defined data-centric tasks. Our controlled empirical study isolates planning horizon as the key architectural feature and systematically analyzes the effects of topological complexity and tool robustness on both paradigms. Our experiments across Knowledge Base Question Answering and Multi-hop QA show that FH planning with lazy replanning achieves accuracy parity with SH across varying depths, breadths, and robustness levels, while using 2-3x fewer tokens. These findings suggest that for well-defined data-centric tasks, eager step-wise monitoring is often unnecessary, and full-horizon planning with on-demand replanning can offer a more efficient default.
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。