mlsanityData to 7 Oct 2026

ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning

arXiv 2603.12740 ↗First posted 13 Mar 2026cs.AIcited by 18

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, current LLM agent tool planning methods typically rely on greedy, reactive tool selection strategies that lack foresight and fail to account for inter-tool dependencies. In this paper, we present ToolTree, a novel Monte Carlo tree search-inspired planning paradigm for tool planning. ToolTree explores possible tool usage trajectories using a dual-stage LLM evaluation and bidirectional pruning mechanism that enables the agent to make informed, adaptive decisions over extended tool-use sequences while pruning less promising branches before and after the tool execution. Empirical evaluations across both open-set and closed-set tool planning tasks on 4 benchmarks demonstrate that ToolTree consistently improves performance while keeping the highest efficiency, achieving an average gain of around 10% compared to the state-of-the-art planning paradigm.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 31 of its 36 references that are in the map. First posted on arXiv 13 Mar 2026.

Builds on

31 of 36 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Tool-Planner: Task Planning with Clusters across Multiple Tools6 Jun
  2. 2024Tool Learning with Large Language Models: A Survey28 May
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  4. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  5. 2023ART: Automatic multi-step reasoning and tool-use for large language models16 Mar
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  9. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  10. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  11. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  12. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
13 more
  1. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  2. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  3. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 195
  4. 2024Tree Search for Language Model Agentscited by 148
  5. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agentscited by 144
  6. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  7. 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agentcited by 108
  8. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  9. 2024GTA: A Benchmark for General Tool Agentscited by 77
  10. 2025OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoningcited by 69
  11. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 59
  12. 2024m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Taskscited by 38
  13. 2024Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chesscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 18.

18 papers.

Sort:

By area:

  1. 2026GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillationcited by 10
  2. 2026Recursive Self-Evolving Agents via Held-Out Selectioncited by 6
  3. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 5
  4. 2026ActorMind: Emulating Human Actor Reasoning for Speech Role-Playingcited by 4
  5. 2026SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregationcited by 3
  6. 2026The Menu Is an Execution Prior: State-Path Tool Menus for Online Agentscited by 2
  7. 2026Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluationcited by 1
  8. 2026Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluationcited by 1
  9. 2026Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agentscited by 1
  10. 2026Learnable Instance Attention Filtering for Adaptive Detector Distillationcited by 0
  11. 2026PAC-CF: Calibrating Irreversible Frontier Pruning in LLM-Guided Searchcited by 0
  12. 2026Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Modelscited by 0
6 more
  1. 2026ToolFG: Towards Well-Grounded Fine-Grained Image Classificationcited by 0
  2. 2026When Does Restricting a Coding Agent to executecode Help? A Regime × Agent-Design Ablationcited by 0
  3. 2026Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Resultcited by 0
  4. 2026Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agentcited by 0
  5. 2026Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agentscited by 0
  6. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnessescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
  2. 2026HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents
  3. 2026DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
  4. 2026PDEU-Bench: Benchmarking the Personalized Planning Lifecycle of Tool-Calling LLM Agents
  5. 2026PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
  6. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
  7. 2025TPS-Bench: Evaluating AI Agents' Tool Planning & Scheduling Abilities in Compounding Tasks
  8. 2026Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction