mlsanityData to 7 Oct 2026

Alignment for Efficient Tool Calling of Large Language Models

arXiv 2503.06708 ↗First posted 9 Mar 2025cs.CLcited by 17

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

Abstract (arXiv)

Recent advancements in tool learning have enabled large language models (LLMs) to integrate external tools, enhancing their task performance by expanding their knowledge boundaries. However, relying on tools often introduces tradeoffs between performance, speed, and cost, with LLMs sometimes exhibiting overreliance and overconfidence in tool usage. This paper addresses the challenge of aligning LLMs with their knowledge boundaries to make more intelligent decisions about tool invocation. We propose a multi objective alignment framework that combines probabilistic knowledge boundary estimation with dynamic decision making, allowing LLMs to better assess when to invoke tools based on their confidence. Our framework includes two methods for knowledge boundary estimation, consistency based and absolute estimation, and two training strategies for integrating these estimates into the model decision making process. Experimental results on various tool invocation scenarios demonstrate the effectiveness of our framework, showing significant improvements in tool efficiency by reducing unnecessary tool usage.

Key facts. Cited by 17 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 37 of its 49 references that are in the map. First posted on arXiv 9 Mar 2025.

Builds on

37 of 49 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Reducing Tool Hallucination via Reliability Alignment5 Dec
  2. 2024Budget-Constrained Tool Learning with Planning25 Feb
  3. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use4 Oct
  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 · 29

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  10. 2020Learning to summarize from human feedbackcited by 2,562
  11. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  12. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
17 more
  1. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  2. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  3. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  4. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  5. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  6. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  7. 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
  8. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 179
  9. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMscited by 162
  10. 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 115
  11. 2023DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scalescited by 107
  12. 2023Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Taskscited by 84
  13. 2024Calibrating Large Language Models with Sample Consistencycited by 72
  14. 2024Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedbackcited by 64
  15. 2023Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learningcited by 29
  16. 2024On the Essence and Prospect: An Investigation of Alignment Approaches for Big Modelscited by 21
  17. 2025Enhancing LLM Reliability via Explicit Knowledge Boundary Modelingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 14.

17 papers.

Sort:

By area:

  1. 2026LLM Agents Already Know When to Call Tools -- Even Without Reasoningcited by 17
  2. 2026Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Servingcited by 16
  3. 2026Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Usecited by 8
  4. 2026AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learningcited by 8
  5. 2025DiSRouter: Distributed Self-Routing for LLM Selectionscited by 5
  6. 2026I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editingcited by 4
  7. 2025Look It Up: Analysing Internal Web Search Capabilities of Modern LLMscited by 3
  8. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2
  9. 2026IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignmentcited by 2
  10. 2026Controlling Tool Use with Heading-Specific Activation Steeringcited by 2
  11. 2026Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Makingcited by 2
  12. 2026DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regressioncited by 1
5 more
  1. 2026RAS: a Reliability Oriented Metric for Automatic Speech Recognitioncited by 0
  2. 2026Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Modelscited by 0
  3. 2026XFlow: An Executable Protocol Programming System for Reliable Multi-Agent Workflowscited by 0
  4. 2026Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applicationscited by 0
  5. 2026Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  2. 2025Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors
  3. 2024Tool Learning with Large Language Models: A Survey
  4. 2024What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks
  5. 2026Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
  6. 2026CoBRA: Learning Tool-Use Boundaries via Counterfactual Margins
  7. 2024Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models
  8. 2024RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning