mlsanityData to 7 Oct 2026

TOOLVERIFIER: Generalization to New Tools via Self-Verification

arXiv 2402.14158 ↗First posted 21 Feb 2024cs.CLcited by 23

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

Abstract (arXiv)

Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem. While there has been significant progress on learning to use specific tools via fine-tuning, language models still struggle with learning how to robustly use new tools from only a few demonstrations. In this work we introduce a self-verification method which distinguishes between close candidates by self-asking contrastive questions during (1) tool selection; and (2) parameter generation. We construct synthetic, high-quality, self-generated data for this goal using Llama-2 70B, which we intend to release publicly. Extensive experiments on 4 tasks from the ToolBench benchmark, consisting of 17 unseen tools, demonstrate an average improvement of 22% over few-shot baselines, even in scenarios where the distinctions between candidate tools are finely nuanced.

Key facts. Cited by 23 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 33 of its 40 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

33 of 40 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  2. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  3. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  4. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  5. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
  7. 2022TALM: Tool Augmented Language Models24 May

Other references · 26

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  8. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  10. 2021Ethical and social risks of harm from Language Modelscited by 957
  11. 2022PAL: Program-aided Language Modelscited by 635
  12. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
14 more
  1. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  2. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  3. 2021Generating Datasets with Pretrained Language Modelscited by 192
  4. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  5. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  6. 2023Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Modelscited by 66
  7. 2023ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Modelscited by 43
  8. 2023Learning to Reason and Memorize with Self-Notescited by 30
  9. 2023The ART of LLM Refinement: Ask, Refine, and Trustcited by 29
  10. 2023Teaching Language Models to Self-Improve through Interactive Demonstrationscited by 26
  11. 2023SELF: Self-Evolution with Language Feedbackcited by 24
  12. 2023SCREWS: A Modular Framework for Reasoning with Revisionscited by 16
  13. 2023Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Datacited by 13
  14. 2023Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspectioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 9; 2026: 7.

23 papers.

Sort:

By area:

  1. 2024Tool Learning with Large Language Models: A Surveycited by 221
  2. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  3. 2025Self-Challenging Language Model Agentscited by 56
  4. 2025CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning taskscited by 30
  5. 2024Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sourcescited by 27
  6. 2024TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Usecited by 11
  7. 2025GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulationcited by 9
  8. 2024When is the consistent prediction likely to be a correct prediction?cited by 8
  9. 2025ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIscited by 8
  10. 2024LLMs can learn self-restraint through iterative self-reflectioncited by 6
  11. 2026Tool Verification for Test-Time Reinforcement Learningcited by 6
  12. 2024Frontier AI Ethics: Anticipating and Evaluating the Societal Impacts of Language Model Agentscited by 5
11 more
  1. 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chainingcited by 5
  2. 2026Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learningcited by 5
  3. 2025NaviAgent: Graph-Driven Bilevel Planning for Scalable Tool Orchestrationcited by 3
  4. 2024SEAL: Suite for Evaluating API-use of LLMscited by 2
  5. 2026Teaching LLMs to Learn Tool Trialing and Execution through Environment Interactioncited by 2
  6. 2026IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignmentcited by 2
  7. 2025TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlerscited by 0
  8. 2025TAPS: Tool-Augmented Personalisation via Structured Taggingcited by 0
  9. 2026Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correctioncited by 0
  10. 2026SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisitioncited by 0
  11. 2026Toolcompass: Guiding Tool Trialing, Not Suppressing Itcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
  2. 2025Self-Training Large Language Models for Tool-Use Without Demonstrations
  3. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  4. 2024LLM With Tools: A Survey
  5. 2025ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning
  6. 2024Learning Evolving Tools for Large Language Models
  7. 2025ToLeaP: Rethinking Development of Tool Learning with Large Language Models
  8. 2023GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution