mlsanityData to 7 Oct 2026

MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models

arXiv 2507.00487 ↗First posted 1 Jul 2025cs.IR cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Tool retrieval is a critical component in enabling large language models (LLMs) to interact effectively with external tools. It aims to precisely filter the massive tools into a small set of candidates for the downstream tool-augmented LLMs. However, most existing approaches primarily focus on optimizing tool representations, often neglecting the importance of precise query comprehension. To address this gap, we introduce MassTool, a multi-task search-based framework designed to enhance both query representation and tool retrieval accuracy. MassTool employs a two-tower architecture: a tool usage detection tower that predicts the need for function calls, and a tool retrieval tower that leverages a query-centric graph convolution network (QC-GCN) for effective query-tool matching. It also incorporates search-based user intent modeling (SUIM) to handle diverse and out-of-distribution queries, alongside an adaptive knowledge transfer (AdaKT) module for efficient multi-task learning. By jointly optimizing tool usage detection loss, list-wise retrieval loss, and contrastive regularization loss, MassTool establishes a robust dual-step sequential decision-making pipeline for precise query understanding. Extensive experiments demonstrate its effectiveness in improving retrieval accuracy. Our code is available at https://github.com/wxydada/MassTool.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 48 of its 56 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

48 of 56 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  8. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  9. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  11. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  12. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
36 more
  1. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  2. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  3. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 426
  4. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  5. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  6. 2024Tool Learning with Large Language Models: A Surveycited by 221
  7. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 209
  8. 2024ToolACE: Winning the Points of LLM Function Callingcited by 204
  9. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  10. 2022TALM: Tool Augmented Language Modelscited by 197
  11. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  12. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 153
  13. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 141
  14. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  15. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 85
  16. 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculumcited by 64
  17. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 61
  18. 2024Hammer: Robust Function-Calling for On-Device Language Models via Function Maskingcited by 53
  19. 2024Natural Language Processing for Dialects of a Language: A Surveycited by 40
  20. 2024ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrievalcited by 40
  21. 2024Towards Completeness-Oriented Tool Retrieval for Large Language Modelscited by 26
  22. 2024Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Searchcited by 24
  23. 2025Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoningcited by 23
  24. 2024Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchangecited by 22
  25. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  26. 2023Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLMcited by 18
  27. 2022A Graph-Enhanced Click Model for Web Searchcited by 17
  28. 2024DemoRank: Selecting Effective Demonstrations for Large Language Models in Ranking Taskcited by 17
  29. 2024Towards Efficient and Effective Unlearning of Large Language Models for Recommendationcited by 16
  30. 2024A Comprehensive Survey on Retrieval Methods in Recommender Systemscited by 16
  31. 2024GeckOpt: LLM System Efficiency via Intent-Based Tool Selectioncited by 12
  32. 2024Improving Tool Retrieval by Leveraging Large Language Models for Query Generationcited by 11
  33. 2024From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIscited by 8
  34. 2024Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Modelscited by 4
  35. 2024Task-Aligned Tool Recommendation for Large Language Modelscited by 3
  36. 2024Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  2. 2026From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skillscited by 15
  3. 2026SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scalecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection
  2. 2024Enhancing Tool Retrieval with Iterative Feedback from Large Language Models
  3. 2025Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
  4. 2026RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
  5. 2025Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval
  6. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph
  7. 2025RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
  8. 2026Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction