mlsanityData to 14 Oct 2026

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution

arXiv 2505.07512 ↗First posted 12 May 2025cs.CL cs.AIcited by 7

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

also in 1 more
Abstract (arXiv)

The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capability primarily rely on distilling advanced models by data synthesis. However, this method incurs significant costs associated with advanced model usage and often results in data compatibility issues, led by the high discrepancy in the knowledge scope between the advanced model and the target model. To address these challenges, we propose ToolACE-DEV, a self-improving framework for tool learning. First, we decompose the tool-learning objective into sub-tasks that enhance basic tool-making and tool-using abilities. Then, we introduce a self-evolving paradigm that allows lightweight models to self-improve, reducing reliance on advanced LLMs. Extensive experiments validate the effectiveness of our approach across models of varying scales and architectures.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 31 of its 42 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

31 of 42 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Hammer: Robust Function-Calling for On-Device Language Models via Function Masking6 Oct
  2. 2024ToolACE: Winning the Points of LLM Function Calling2 Sep
  3. 2024Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks27 Jun
  4. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets26 Jun
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  6. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  7. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 23

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  8. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  9. 2023Teaching Large Language Models to Self-Debugcited by 988
  10. 2023BloombergGPT: A Large Language Model for Financecited by 939
  11. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  12. 2022Large Language Models Can Self-Improvecited by 664
11 more
  1. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 557
  2. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 500
  3. 2023Solving Math Word Problems by Combining Language Models With Symbolic Solverscited by 124
  4. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 111
  5. 2024RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Foldcited by 99
  6. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 93
  7. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 87
  8. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 86
  9. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
  10. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usagecited by 55
  11. 2023Ada-Instruct: Adapting Instruction Generators for Complex Reasoningcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2026Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoningcited by 15
  2. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 14
  3. 2025GRAM-R2: Self-Training Generative Foundation Reward Models for Reward Reasoningcited by 7
  4. 2026iReasoner: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Modelscited by 7
  5. 2026Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoningcited by 7
  6. 2026Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMscited by 1
  7. 2026VESTA: Visual Exploration with Statistical Tool Agentscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning
  2. 2024Learning Evolving Tools for Large Language Models
  3. 2025ToLeaP: Rethinking Development of Tool Learning with Large Language Models
  4. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  5. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
  6. 2024TOOLVERIFIER: Generalization to New Tools via Self-Verification
  7. 2024Tool Learning with Large Language Models: A Survey
  8. 2024What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks