mlsanityData to 7 Oct 2026

Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation

arXiv 2501.12432 ↗First posted 21 Jan 2025cs.LG cs.AI cs.CLcited by 16

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

Abstract (arXiv)

Although current Large Language Models (LLMs) exhibit impressive capabilities, performing complex real-world tasks still requires tool learning. Mainstream methods, such as CoT/ReAct, rely on step-by-step tool invocation to interact with external environments, but they are limited in perceptual scope and lack adequate task-planning capability. To address these limitations, other studies introduce the first Search-based Decision Tree (DFSDT), which still suffers from the high computational cost. In this paper, we introduce a novel parallel tool invocation paradigm, DTA-Llama (Divide-Then-Aggregate Llama). First, we transform traditional tree-based tool search paths into Directed Acyclic Graph (DAG) structure, generating a high-quality parallel tool invocation dataset. The DTA-Llama is then trained on the dataset to learn to iteratively divide the current task into several parallel tool invocation sub-tasks and aggregate the invocation results to decide the next actions. Furthermore, we introduce an efficient inference framework inspired by the Process/Threads mechanism when applying the DTA-Llama to practical tasks. Experimental results show that our approach substantially enhances task performance while reducing token consumption and inference time. Llama2-7B, using our method, is comparable to the official parallel function calling method of GPT-3.5. The relevant code, dataset, and model weights are available at https://corn0205.github.io/

Key facts. Cited by 16 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 42 references that are in the map. First posted on arXiv 21 Jan 2025.

Builds on

31 of 42 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024ToolACE: Winning the Points of LLM Function Calling2 Sep
  2. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents26 May
  3. 2024Learning to Use Tools via Cooperative and Interactive Agents5 Mar
  4. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls6 Feb
  5. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction11 Jan
  6. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use4 Oct
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  8. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  9. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  10. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  11. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  8. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  9. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  10. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  11. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  12. 2023An LLM Compiler for Parallel Function Callingcited by 170
8 more
  1. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  2. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  3. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  4. 2024Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Treescited by 38
  5. 2024LAMBDA: A Large Model Based Data Agentcited by 30
  6. 2023Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Modelcited by 29
  7. 2024VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimizationcited by 16
  8. 2022SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 6.

16 papers.

Sort:

By area:

  1. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  2. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agentscited by 36
  3. 2025Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoningcited by 16
  4. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  5. 2026ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decodingcited by 4
  6. 2025ATTS: Asynchronous Test-Time Scaling via Conformal Predictioncited by 3
  7. 2025ParaCook: On Time-Efficient Planning for Multi-Agent Systemscited by 2
  8. 2025Large Language Models for Zero-Shot Multicultural Name Recognitioncited by 1
  9. 2025LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generationcited by 1
  10. 2025LVLM-Composer's Explicit Planning for Image Generationcited by 0
  11. 2025VisuCraft: Enhancing Large Vision-Language Models for Complex Visual-Guided Creative Content Generation via Structured Information Extractioncited by 0
  12. 2025MM-FusionNet: Context-Aware Dynamic Fusion for Multi-modal Fake News Detection with Large Vision-Language Modelscited by 0
4 more
  1. 2026Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correctioncited by 0
  2. 2026HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptationcited by 0
  3. 2026Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflowscited by 0
  4. 2026ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Alignment for Efficient Tool Calling of Large Language Models
  2. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  3. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph
  4. 2026Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
  5. 2026Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees
  6. 2024Tool-Planner: Task Planning with Clusters across Multiple Tools
  7. 2024Tool Learning with Large Language Models: A Survey
  8. 2025HGMF: A Hierarchical Gaussian Mixture Framework for Scalable Tool Invocation within the Model Context Protocol