mlsanityData to 7 Oct 2026

TALM: Tool Augmented Language Models

arXiv 2205.12255 ↗First posted 24 May 2022cs.CL cs.AIcited by 197

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

Abstract (arXiv)

Transformer based language models (LMs) demonstrate increasing performance with scale across a wide variety of tasks. Scale alone however cannot enable models to solve tasks that require access to ephemeral, changing, or private data that was unavailable at training time. Many useful tasks may also benefit from LMs being able to access APIs that read or modify state. In this work, we present Tool Augmented Language Models (TALM), combining a text-only approach to augment language models with non-differentiable tools, and an iterative "self-play" technique to bootstrap performance starting from few tool demonstrations. TALM exhibits strong performance on both a knowledge-heavy QA task and a reasoning oriented math task with simple tools. At a given model scale, TALM significantly outperforms non-augmented LMs. We further demonstrate that TALM successfully performs out-of-distribution inferences on both QA and math tasks, where non-augmented LMs fail. Our results suggest that Tool Augmented Language Models are a promising direction to enrich LMs' capabilities, with less dependence on scale.

Key facts. Cited by 197 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 17 of its 21 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

17 of 21 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  9. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  12. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
5 more
  1. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  2. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
  3. 2022Scaling Up Models and Data with textttt5x and textttseqiocited by 187
  4. 2018Supervising strong learners by amplifying weak expertscited by 139
  5. 2019Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehensioncited by 51

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 62; 2024: 67; 2025: 39; 2026: 27.

197 papers.

Sort:

By area:

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  2. 2023A Survey of Large Language Modelscited by 2,537
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  4. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  5. 2023A Survey on Multimodal Large Language Modelscited by 898
  6. 2023A Comprehensive Overview of Large Language Modelscited by 639
  7. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  8. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  9. 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructionscited by 441
  10. 2023Cognitive Architectures for Language Agentscited by 422
  11. 2023Augmented Language Models: a Surveycited by 398
  12. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
38 more
  1. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 350
  2. 2023Tool Learning with Foundation Modelscited by 302
  3. 2023Large Language Models as Tool Makerscited by 293
  4. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  5. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  6. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  7. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  8. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 241
  9. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  10. 2024Tool Learning with Large Language Models: A Surveycited by 221
  11. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  12. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 200
  13. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 193
  14. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  15. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  16. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  17. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 150
  18. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
  19. 2023LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agentcited by 134
  20. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  21. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  22. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  23. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 121
  24. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  25. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  26. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  27. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  28. 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 115
  29. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 111
  30. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  31. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  32. 2024AIOS: LLM Agent Operating Systemcited by 94
  33. 2024Teams of LLM Agents can Exploit Zero-Day Vulnerabilitiescited by 93
  34. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 85
  35. 2022Mind's Eye: Grounded Language Model Reasoning through Simulationcited by 83
  36. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  37. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  38. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Recordscited by 75

50 most cited of 197 All 197 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024LLM Augmented LLMs: Expanding Capabilities through Composition
  2. 2025Benchmarking Failures in Tool-Augmented Language Models
  3. 2024LLM With Tools: A Survey
  4. 2024MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning
  5. 2025OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models
  6. 2025Can abstract concepts from LLM improve SLM performance?
  7. 2024metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models
  8. 2025A Survey on Large Language Models with some Insights on their Capabilities and Limitations