mlsanityData to 7 Oct 2026

Toolformer: Language Models Can Teach Themselves to Use Tools

arXiv 2302.04761 ↗First posted 9 Feb 2023cs.CLcited by 4,072

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

Abstract (arXiv)

Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with basic functionality, such as arithmetic or factual lookup, where much simpler and smaller models excel. In this paper, we show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds. We introduce Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction. This is done in a self-supervised way, requiring nothing more than a handful of demonstrations for each API. We incorporate a range of tools, including a calculator, a Q&A system, two different search engines, a translation system, and a calendar. Toolformer achieves substantially improved zero-shot performance across a variety of downstream tasks, often competitive with much larger models, without sacrificing its core language modeling abilities.

Key facts. Cited by 4,072 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 39 of its 63 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

39 of 63 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022TALM: Tool Augmented Language Models24 May

Other references · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2016Pointer Sentinel Mixture Modelscited by 2,992
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  10. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  12. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
26 more
  1. 2019Language Models as Knowledge Bases?cited by 1,922
  2. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  3. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  4. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  6. 2019How Can We Know What Language Models Know?cited by 953
  7. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  8. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  9. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  10. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  11. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  12. 2022PAL: Program-aided Language Modelscited by 635
  13. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  14. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 544
  15. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  16. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 339
  17. 2016FastText.zip: Compressing text classification modelscited by 331
  18. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 314
  19. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 290
  20. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  21. 2021Internet-Augmented Dialogue Generationcited by 217
  22. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 197
  23. 2021Generating Datasets with Pretrained Language Modelscited by 192
  24. 2019Revisiting Self-Training for Neural Sequence Generationcited by 154
  25. 2022PEER: A Collaborative Language Modelcited by 86
  26. 2021HTLM: Hyper-Text Pre-Training and Prompting of Language Modelscited by 58

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 447; 2024: 668; 2025: 845; 2026: 2112.

4,072 papers.

Sort:

By area:

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023Qwen Technical Reportcited by 3,273
  5. 2023A Survey of Large Language Modelscited by 2,537
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  11. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  12. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
38 more
  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  4. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  5. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  6. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  7. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  8. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  9. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  10. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  11. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  12. 2023A Survey on Multimodal Large Language Modelscited by 898
  13. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  14. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  15. 2023Large Language Models as Optimizerscited by 830
  16. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  17. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  18. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  19. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  20. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  21. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  22. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  23. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  24. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  25. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  26. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  27. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  28. 2023Segment Everything Everywhere All at Oncecited by 546
  29. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  30. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 527
  31. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  32. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
  33. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  34. 2023Active Retrieval Augmented Generationcited by 506
  35. 2024Large Language Models: A Surveycited by 506
  36. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  37. 2024InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agentscited by 476
  38. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 465

50 most cited of 4,072 All 4,072 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Re-Initialization Token Learning for Tool-Augmented Large Language Models
  2. 2025TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlers
  3. 2025ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
  4. 2024ToolACE: Winning the Points of LLM Function Calling
  5. 2025Benchmarking Failures in Tool-Augmented Language Models
  6. 2025When2Call: When (not) to Call Tools
  7. 2024Better & Faster Large Language Models via Multi-token Prediction
  8. 2026Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls