# Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning arXiv: https://arxiv.org/abs/2511.10037 ยท HTML: https://mlsanity.com/paper/2511.10037/ ## Key facts - Cited by 17 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 16 of its 39 references that are in the map. - First posted on arXiv 13 Nov 2025. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/) ## Builds on (most cited first, 16 of 16) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025) - [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023) - [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023) - [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025) - [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023) - [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020) - [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022) - [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023) - [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023) - [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025) - [Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering](https://mlsanity.com/paper/2401.08500/) (2024) - [ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models](https://mlsanity.com/paper/2309.00986/) (2023) - [Towards AI Search Paradigm](https://mlsanity.com/paper/2506.17188/) (2025) - [Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation](https://mlsanity.com/paper/2501.12432/) (2025) - [TURA: Tool-Augmented Unified Retrieval Agent for AI Search](https://mlsanity.com/paper/2508.04604/) (2025) ## Built on by (most cited first, 17 of 17) - [When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents](https://mlsanity.com/paper/2606.05806/) (2026) - [Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery](https://mlsanity.com/paper/2603.05860/) (2026) - [PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning](https://mlsanity.com/paper/2602.13691/) (2026) - [Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning](https://mlsanity.com/paper/2603.15371/) (2026) - [Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination](https://mlsanity.com/paper/2604.24978/) (2026) - [MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection](https://mlsanity.com/paper/2604.27934/) (2026) - [Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering](https://mlsanity.com/paper/2607.25090/) (2026) - [STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning](https://mlsanity.com/paper/2605.10057/) (2026) - [Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling](https://mlsanity.com/paper/2605.19418/) (2026) - [DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance](https://mlsanity.com/paper/2606.05728/) (2026) - [Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization](https://mlsanity.com/paper/2602.15854/) (2026) - [Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction](https://mlsanity.com/paper/2602.18968/) (2026) - [UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning](https://mlsanity.com/paper/2604.05517/) (2026) - [Retrieval-Augmented Multimodal Model for Fake News Detection](https://mlsanity.com/paper/2604.18112/) (2026) - [From Intent to Execution: Composing Agentic Workflows with Agent Recommendation](https://mlsanity.com/paper/2605.03986/) (2026) - [PersonalPlan: Planning Multi-Agent Systems for Personalized Programming Learning](https://mlsanity.com/paper/2606.18633/) (2026) - [Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs](https://mlsanity.com/paper/2610.14209/) (2026) ## Abstract (arXiv) 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.