Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning

• URL: http://arxiv.org/abs/2511.10037v1
• Date: Fri, 14 Nov 2025 01:27:38 GMT
• Title: Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
• Abstract summary: We propose a Planner-centric Plan-Execute paradigm to resolve local optimization bottlenecks.<n>A novel Planner model performs global Directed Acyclic Graph (DAG) planning for complex queries.<n>We also introduce ComplexTool-Plan, a large-scale benchmark dataset featuring complex queries.<n>When integrated with a capable executor, our framework achieves state-of-the-art performance on the StableToolBench benchmark for complex user queries.
• Score: 31.679428422518082
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing tool-augmented large language models (LLMs) encounter significant challenges when processing complex queries. Current frameworks such as ReAct are prone to local optimization traps due to their reliance on incremental decision-making processes. To address these limitations, we propose a novel Planner-centric Plan-Execute paradigm that fundamentally resolves local optimization bottlenecks through architectural innovation. Central to our approach is a novel Planner model that performs global Directed Acyclic Graph (DAG) planning for complex queries, enabling optimized execution beyond conventional tool coordination. We also introduce ComplexTool-Plan, a large-scale benchmark dataset featuring complex queries that demand sophisticated multi-tool composition and coordination capabilities. Additionally, we develop a two-stage training methodology that integrates Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), systematically enhancing the Planner's tool selection accuracy and global planning awareness through structured DAG-based planning. When integrated with a capable executor, our framework achieves state-of-the-art performance on the StableToolBench benchmark for complex user queries, demonstrating superior end-to-end execution capabilities and robust handling of intricate multi-tool workflows.

Related papers

• EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
  We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
  arXiv  Detail & Related papers  (2026-08-05T08:50:36Z)
• OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization [49.99886124874474]
  OPERA is a framework that jointly optimize restoration planning and tool execution in an end-to-end manner.<n> OPERA consistently outperforms both all-in-one restoration models and existing agent-based methods across diverse and complex degradation scenarios.
  arXiv  Detail & Related papers  (2026-05-21T07:40:25Z)
• 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)
• Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning [32.56971325545821]
  Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions.<n>We propose an enhanced multi-agent framework that decomposes automation into three roles: a planner for high-level decision-making, an actor for task execution, and a memory manager for contextual reasoning.
  arXiv  Detail & Related papers  (2026-05-04T02:58:05Z)
• 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)
• A Unified Framework for Automated Assembly Sequence and Production Line Planning using Graph-based Optimization [0.688175992229959]
  PyCAALP is a framework for automated Assembly Sequence Planning (ASP) and Production Line Planning (PLP)<n>The framework integrates kinematic boundary conditions, such as potential part collisions, to guarantee the feasibility of automated assembly planning.<n>The framework promotes further collaboration and adoption in both industrial and production research applications.
  arXiv  Detail & Related papers  (2025-12-15T11:32:45Z)
• Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Tasks [0.0]
  We introduce RP-ReAct, a novel multi-agent approach that decouples strategic planning from low-level execution to achieve superior reliability and efficiency.<n>RP-ReAct consists of a Reasoner Planner Agent (RPA), responsible for planning each sub-step, and one or multiple Proxy-Execution Agent (PEA) that translates sub-steps into concrete tool interactions.<n>We evaluate RP-ReAct, on the challenging, multi-domain ToolQA benchmark using a diverse set of six open-weight reasoning models.
  arXiv  Detail & Related papers  (2025-12-03T08:28:40Z)
• GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning [20.75113227786218]
  Graph-based Agent Planning (GAP) is a novel framework that explicitly models inter-task dependencies through graph-based planning.<n>Our approach trains agent foundation models to decompose complex tasks into dependency-aware sub-task graphs.<n>This dependency-aware orchestration achieves substantial improvements in both execution efficiency and task accuracy.
  arXiv  Detail & Related papers  (2025-10-29T09:35:55Z)
• PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving [66.42260489147617]
  We introduce PLAN-TUNING, a framework that distills synthetic task decompositions from large-scale language models.<n>Plan-TUNING fine-tunes smaller models via supervised and reinforcement-learning objectives to improve complex reasoning.<n>Our analysis demonstrates how planning trajectories improves complex reasoning capabilities.
  arXiv  Detail & Related papers  (2025-07-10T07:30:44Z)
• 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)
• Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification [5.727096041675994]
  Large Language Models (LLMs) have shown promise as robotic planners but often struggle with long-horizon and complex tasks.<n>We propose a neuro-symbolic approach that enhances LLMs-based planners with Knowledge Graph-based RAG for hierarchical plan generation.
  arXiv  Detail & Related papers  (2025-04-06T18:36:30Z)
• PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving [89.60370366013142]
  We propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents.<n>Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms.
  arXiv  Detail & Related papers  (2025-02-22T06:21:56Z)
• CogPlanner: Unveiling the Potential of Agentic Multimodal Retrieval Augmented Generation with Planning [9.027579000292441]
  Multimodal Retrieval Augmented Generation (MRAG) systems have shown promise in enhancing the generation capabilities of multimodal large language models (MLLMs)<n>Existing MRAG frameworks primarily adhere to rigid, single-step retrieval strategies that fail to address real-world challenges of information acquisition and query reformulation.<n>We introduce the task of Multimodal Retrieval Augmented Generation Planning (MRAG Planning) that aims at effective information seeking and integration while minimizing computational overhead.
  arXiv  Detail & Related papers  (2025-01-26T10:16:42Z)
• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios [93.68764280953624]
  UltraTool is a novel benchmark designed to improve and evaluate Large Language Models' ability in tool utilization. It emphasizes real-world complexities, demanding accurate, multi-step planning for effective problem-solving. A key feature of UltraTool is its independent evaluation of planning with natural language, which happens before tool usage.
  arXiv  Detail & Related papers  (2024-01-30T16:52:56Z)

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.