mlsanityData to 14 Oct 2026

Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs

arXiv 2606.09371 ↗First posted 8 Jun 2026cs.AIcited by 0

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

Abstract (arXiv)

Tool learning enables LLMs to invoke external tools to accomplish tasks. Prior studies have demonstrated the effectiveness of a hierarchical structure: a high-level policy handles global planning and decomposes tasks into manageable sub-tasks, and a low-level policy focuses on invoking tools to solve these sub-tasks. However, these works typically optimize the high-level and low-level policies separately, leading to planner-executor misalignment and limiting LLM performance on tool-use tasks. In this paper, we propose a method called Capability-Aligned Hierarchical Learning (CAHL), which leverages RLVR to jointly optimize both policies, enabling better alignment between the high-level planner and the low-level executor. Experiments on constrained tool-use benchmarks (API-Bank and BFCL) and an open-ended environment (Bamboogle) demonstrate the effectiveness of CAHL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 16 of its 25 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

16 of 25 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction11 Jan
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  3. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  4. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs14 Apr
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 11

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  2. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  3. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  4. 2023Language Models can Solve Computer Taskscited by 372
  5. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  6. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  7. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 177
  8. 2024StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learningcited by 25
  9. 2025Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Modelcited by 20
  10. 2025TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixturecited by 15
  11. 2025ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback
  2. 2024Tool-Planner: Task Planning with Clusters across Multiple Tools
  3. 2024CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
  4. 2025A Roadmap to Guide the Integration of LLMs in Hierarchical Planning
  5. 2026Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents
  6. 2023LLM Augmented Hierarchical Agents
  7. 2026MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
  8. 2026Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction