mlsanityData to 14 Oct 2026

ProTIP: Progressive Tool Retrieval Improves Planning

arXiv 2312.10332 ↗First posted 16 Dec 2023cs.IR cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes. Two prevalent approaches for TR are single-step retrieval, which utilizes the complete query, and sequential retrieval using task decomposition (TD), where a full query is segmented into discrete atomic subtasks. While single-step retrieval lacks the flexibility to handle "inter-tool dependency," the TD approach necessitates maintaining "subtask-tool atomicity alignment," as the toolbox can evolve dynamically. To address these limitations, we introduce the Progressive Tool retrieval to Improve Planning (ProTIP) framework. ProTIP is a lightweight, contrastive learning-based framework that implicitly performs TD without the explicit requirement of subtask labels, while simultaneously maintaining subtask-tool atomicity. On the ToolBench dataset, ProTIP outperforms the ChatGPT task decomposition-based approach by a remarkable margin, achieving a 24% improvement in Recall@K=10 for TR and a 41% enhancement in tool accuracy for plan generation.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 16 Dec 2023.

Builds on

35 of 54 references.

References · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  10. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  11. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  12. 2020Longformer: The Long-Document Transformercited by 3,413
23 more
  1. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  3. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  4. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  6. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  7. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  8. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  9. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  10. 2023StarCoder: may the source be with you!cited by 799
  11. 2014Distributed Representations of Sentences and Documentscited by 678
  12. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  13. 2018Universal Sentence Encodercited by 489
  14. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  15. 2023Language Models can Solve Computer Taskscited by 372
  16. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 144
  17. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)cited by 85
  18. 2019Analogies Explained: Towards Understanding Word Embeddingscited by 64
  19. 2015Towards Universal Paraphrastic Sentence Embeddingscited by 60
  20. 2019Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehensioncited by 51
  21. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agentscited by 32
  22. 2015A Hierarchical Neural Autoencoder for Paragraphs and Documentscited by 26
  23. 2016Neural Information Retrieval: A Literature Reviewcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 3.

12 papers.

  1. 2024Tool Learning with Large Language Models: A Surveycited by 223
  2. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 158
  3. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23
  4. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  5. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  6. 2024Enhancing Tool Retrieval with Iterative Feedback from Large Language Modelscited by 17
  7. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 16
  8. 2025Graph RAG-Tool Fusioncited by 15
  9. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systemscited by 15
  10. 2025Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systemscited by 4
  11. 2026PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Modelscited by 4
  12. 2026CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrievalcited by 0