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

arXiv: https://arxiv.org/abs/2502.12961 · HTML: https://mlsanity.com/paper/2502.12961/

## 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.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 28 of 28)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation](https://mlsanity.com/paper/2307.11019/) (2023)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [Solving Math Word Problems by Combining Language Models With Symbolic Solvers](https://mlsanity.com/paper/2304.09102/) (2023)
- [Efficient Nearest Neighbor Language Models](https://mlsanity.com/paper/2109.04212/) (2021)
- [BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents](https://mlsanity.com/paper/2308.05960/) (2023)
- [Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks](https://mlsanity.com/paper/2307.00175/) (2023)
- [Aligning Large Language Models with Human Preferences through Representation Engineering](https://mlsanity.com/paper/2312.15997/) (2023)
- [On the Pitfalls of Analyzing Individual Neurons in Language Models](https://mlsanity.com/paper/2110.07483/) (2021)
- [You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM](https://mlsanity.com/paper/2210.15859/) (2022)
- [CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking](https://mlsanity.com/paper/2502.09635/) (2025)

## Built on by (most cited first, 30 of 30)

- [Acting Less is Reasoning More! Teaching Model to Act Efficiently](https://mlsanity.com/paper/2504.14870/) (2025)
- [DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks](https://mlsanity.com/paper/2509.01396/) (2025)
- [AdaTooler-V: Adaptive Tool-Use for Images and Videos](https://mlsanity.com/paper/2512.16918/) (2025)
- [A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions](https://mlsanity.com/paper/2504.16939/) (2025)
- [Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use](https://mlsanity.com/paper/2605.14038/) (2026)
- [A Review of Incorporating Psychological Theories in LLMs](https://mlsanity.com/paper/2505.00003/) (2025)
- [Characterizing Web Search in The Age of Generative AI](https://mlsanity.com/paper/2510.11560/) (2025)
- [AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents](https://mlsanity.com/paper/2603.09716/) (2026)
- [MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design](https://mlsanity.com/paper/2507.20541/) (2025)
- [Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning](https://mlsanity.com/paper/2511.04341/) (2025)
- [Multi-Step Reasoning for Embodied Question Answering via Tool Augmentation](https://mlsanity.com/paper/2510.20310/) (2025)
- [Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models](https://mlsanity.com/paper/2602.12996/) (2026)
- [Beyond the Black Box: Interpretability of Agentic AI Tool Use](https://mlsanity.com/paper/2605.06890/) (2026)
- [Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets](https://mlsanity.com/paper/2505.20120/) (2025)
- [Fast, Slow, and Tool-augmented Thinking for LLMs: A Review](https://mlsanity.com/paper/2508.12265/) (2025)
- [Fine-Tuning Language Models to Know What They Know](https://mlsanity.com/paper/2602.02605/) (2026)
- [Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents](https://mlsanity.com/paper/2604.05808/) (2026)
- [Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty](https://mlsanity.com/paper/2604.17293/) (2026)
- [Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making](https://mlsanity.com/paper/2607.14277/) (2026)
- [Future Confidence Distillation in Large Language Models](https://mlsanity.com/paper/2607.07626/) (2026)
- [Metacognition in LLMs: Foundations, Progress, and Opportunities](https://mlsanity.com/paper/2607.11881/) (2026)
- [Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.16453/) (2026)
- [Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning](https://mlsanity.com/paper/2609.38147/) (2026)
- [MA2P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion](https://mlsanity.com/paper/2605.18572/) (2026)
- [MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design](https://mlsanity.com/paper/2606.14202/) (2026)
- [Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognition](https://mlsanity.com/paper/2608.23029/) (2026)
- [A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models](https://mlsanity.com/paper/2609.04409/) (2026)
- [Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents](https://mlsanity.com/paper/2609.27869/) (2026)
- [When Does Action Credit Need Updating?](https://mlsanity.com/paper/2609.29007/) (2026)
- [SciCurateBench: Curating Experimental Data from Heterogeneous Scientific Literature with Verbal-Action Agents](https://mlsanity.com/paper/2610.14393/) (2026)

## 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.