Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling

• URL: http://arxiv.org/abs/2605.08477v1
• Date: Fri, 08 May 2026 20:51:42 GMT
• Title: Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling
• Abstract summary: LLM-based agents solve complex data-centric tasks, which require precise tool calling over external data sources.<n>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.
• Score: 18.782893288656044
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models [52.48858778580074]
  Planning is a fundamental capability for large language models (LLMs)<n>PlanningBench is a framework for generating scalable, diverse, verifiable planning data for both evaluation and training.
  arXiv  Detail & Related papers  (2026-05-20T08:10:15Z)
• Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams [11.964765256346857]
  Long-horizon task planning for heterogeneous multi-robot systems is essential for deploying collaborative teams in real-world environments.<n>We present Scale-Plan, a scalable LLM-assisted framework that generates compact, task-relevant problem representations from natural language instructions.<n>By filtering irrelevant information prior to planning, Scale-Plan enables efficient decomposition, allocation, and long-horizon plan generation.
  arXiv  Detail & Related papers  (2026-03-09T18:13:18Z)
• TodoEvolve: Learning to Architect Agent Planning Systems [68.48983335970901]
  TodoEvolve is a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning.<n>PlanFactory provides a common interface for heterogeneous planning patterns.<n>TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead.
  arXiv  Detail & Related papers  (2026-02-08T06:37:01Z)
• DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping [74.34061104176554]
  We propose DeepPlanner, an end-to-end RL framework that effectively enhances the planning capabilities of deep research agents.<n>Our approach shapes token-level advantage with an entropy-based term to allocate larger updates to high entropy tokens, and selectively upweights sample-level advantages for planning-intensive rollouts.
  arXiv  Detail & Related papers  (2025-10-14T20:47:05Z)
• HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking [109.09735490692202]
  We propose HyperTree Planning (HTP), a novel reasoning paradigm that constructs hypertree-structured planning outlines for effective planning.<n> Experiments demonstrate the effectiveness of HTP, achieving state-of-the-art accuracy on the TravelPlanner benchmark with Gemini-1.5-Pro, resulting in a 3.6 times performance improvement over o1-preview.
  arXiv  Detail & Related papers  (2025-05-05T02:38:58Z)
• Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos [48.15438373870542]
  VidAssist is an integrated framework designed for zero/few-shot goal-oriented planning in instructional videos. It employs a breadth-first search algorithm for optimal plan generation. Experiments demonstrate that VidAssist offers a unified framework for different goal-oriented planning setups.
  arXiv  Detail & Related papers  (2024-09-30T17:57:28Z)
• On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability [59.72892401927283]
  We evaluate the planning capabilities of OpenAI's o1 models across a variety of benchmark tasks. Our results reveal that o1-preview outperforms GPT-4 in adhering to task constraints.
  arXiv  Detail & Related papers  (2024-09-30T03:58:43Z)
• Long-horizon Embodied Planning with Implicit Logical Inference and Hallucination Mitigation [7.668848364013772]
  We present ReLEP, a novel framework for Real-time Long-horizon Embodied Planning.<n>ReLEP can complete a wide range of long-horizon tasks without in-context examples by learning implicit logical inference through fine-tuning.
  arXiv  Detail & Related papers  (2024-09-24T01:47:23Z)
• Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following [17.608330952846075]
  Embodied Instruction Following (EIF) is the task of executing natural language instructions by navigating and interacting with objects in interactive environments.<n>A key challenge in EIF is compositional task planning, typically addressed through supervised learning or few-shot in-context learning with labeled data.<n>We introduce the Socratic Planner, a self-QA-based zero-shot planning method that infers an appropriate plan without any further training.
  arXiv  Detail & Related papers  (2024-04-21T08:10:20Z)
• Parting with Misconceptions about Learning-based Vehicle Motion Planning [30.39229175273061]
  nuPlan marks a new era in vehicle motion planning research. Existing systems struggle to simultaneously meet both requirements. We propose an extremely simple and efficient planner which outperforms an extensive set of competitors.
  arXiv  Detail & Related papers  (2023-06-13T17:57:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.