mlsanityData to 14 Oct 2026

Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger

arXiv 2502.12961 ↗First posted 18 Feb 2025cs.CL cs.AIcited by 30

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

Abstract (arXiv)

Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that require specialized processing or up-to-date data. While existing research expands LLMs access to diverse tools (e.g., program interpreters, search engines, calculators), the necessity of using these tools is often overlooked, leading to indiscriminate tool invocation. This naive approach raises two key issues: increased latency due to unnecessary tool calls, and potential errors resulting from faulty interactions with external tools. In this paper, we introduce meta-cognition as a proxy for LLMs self-assessment of their capabilities, reflecting the model's awareness of its own limitations. Based on this, we propose MeCo, an adaptive decision-making strategy for external tool use. MeCo quantifies metacognitive scores by capturing high-level cognitive signals in the representation space, guiding when to invoke tools. Notably, MeCo is fine-tuning-free and incurs minimal cost. Experiments across multiple backbone models and benchmarks show that MeCo reliably detects LLMs' internal cognitive signals and significantly improves tool-use decision-making.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 28 of its 52 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

28 of 52 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024ToolACE: Winning the Points of LLM Function Calling2 Sep
  2. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets26 Jun
  3. 2024Tool Learning with Large Language Models: A Survey28 May
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  5. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  6. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  7. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 20

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  3. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  6. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  7. 2023Explainability for Large Language Models: A Surveycited by 333
  8. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 318
  9. 2021Internet-Augmented Dialogue Generationcited by 217
  10. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 164
  11. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  12. 2018Dissecting Contextual Word Embeddings: Architecture and Representationcited by 146
8 more
  1. 2023Solving Math Word Problems by Combining Language Models With Symbolic Solverscited by 124
  2. 2021Efficient Nearest Neighbor Language Modelscited by 93
  3. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agentscited by 84
  4. 2023Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblockscited by 78
  5. 2023Aligning Large Language Models with Human Preferences through Representation Engineeringcited by 71
  6. 2021On the Pitfalls of Analyzing Individual Neurons in Language Modelscited by 62
  7. 2022You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LMcited by 18
  8. 2025CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checkingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 19.

30 papers.

Sort:

By area:

  1. 2025Acting Less is Reasoning More! Teaching Model to Act Efficientlycited by 80
  2. 2025DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Taskscited by 24
  3. 2025AdaTooler-V: Adaptive Tool-Use for Images and Videoscited by 21
  4. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  5. 2026Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Usecited by 7
  6. 2025A Review of Incorporating Psychological Theories in LLMscited by 6
  7. 2025Characterizing Web Search in The Age of Generative AIcited by 5
  8. 2026AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agentscited by 5
  9. 2025MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Designcited by 4
  10. 2025Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoningcited by 4
  11. 2025Multi-Step Reasoning for Embodied Question Answering via Tool Augmentationcited by 3
  12. 2026Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Modelscited by 3
18 more
  1. 2026Beyond the Black Box: Interpretability of Agentic AI Tool Usecited by 3
  2. 2025Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Marketscited by 2
  3. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2
  4. 2026Fine-Tuning Language Models to Know What They Knowcited by 2
  5. 2026Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agentscited by 2
  6. 2026Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertaintycited by 2
  7. 2026Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Makingcited by 2
  8. 2026Future Confidence Distillation in Large Language Modelscited by 1
  9. 2026Metacognition in LLMs: Foundations, Progress, and Opportunitiescited by 1
  10. 2026Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generationcited by 1
  11. 2026Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoningcited by 1
  12. 2026MA2P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasioncited by 0
  13. 2026MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Designcited by 0
  14. 2026Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognitioncited by 0
  15. 2026A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Modelscited by 0
  16. 2026Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agentscited by 0
  17. 2026When Does Action Credit Need Updating?cited by 0
  18. 2026SciCurateBench: Curating Experimental Data from Heterogeneous Scientific Literature with Verbal-Action Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Meta-Reasoning Improves Tool Use in Large Language Models
  2. 2026Decomposing and Steering Functional Metacognition in Large Language Models
  3. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
  4. 2025Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens
  5. 2024LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
  6. 2026LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
  7. 2026Think2: Grounded Metacognitive Reasoning in Large Language Models
  8. 2024LLM With Tools: A Survey