# When2Call: When (not) to Call Tools

arXiv: https://arxiv.org/abs/2504.18851 · HTML: https://mlsanity.com/paper/2504.18851/

## Key facts

- Cited by 42 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 19 of its 30 references that are in the map.
- First posted on arXiv 26 Apr 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, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024)
- [xLAM: A Family of Large Action Models to Empower AI Agent Systems](https://mlsanity.com/paper/2409.03215/) (2024)
- [Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks](https://mlsanity.com/paper/2407.00121/) (2024)
- [Changing Answer Order Can Decrease MMLU Accuracy](https://mlsanity.com/paper/2406.19470/) (2024)
- [NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment](https://mlsanity.com/paper/2405.01481/) (2024)
- [API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs](https://mlsanity.com/paper/2402.15491/) (2024)

## Built on by (most cited first, 30 of 42)

- [NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model](https://mlsanity.com/paper/2508.14444/) (2025)
- [Structured Uncertainty guided Clarification for LLM Agents](https://mlsanity.com/paper/2511.08798/) (2025)
- [COMPASS: Benchmarking Constrained Optimization in LLM Agents](https://mlsanity.com/paper/2510.07043/) (2025)
- [Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception](https://mlsanity.com/paper/2510.23853/) (2025)
- [To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling](https://mlsanity.com/paper/2605.00737/) (2026)
- [Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use](https://mlsanity.com/paper/2605.14038/) (2026)
- [Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains](https://mlsanity.com/paper/2510.17793/) (2025)
- [From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents](https://mlsanity.com/paper/2605.15104/) (2026)
- [Agentic Tool Use in Large Language Models](https://mlsanity.com/paper/2604.00835/) (2026)
- [Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning](https://mlsanity.com/paper/2606.06976/) (2026)
- [When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation](https://mlsanity.com/paper/2607.07050/) (2026)
- [Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents](https://mlsanity.com/paper/2607.27083/) (2026)
- [RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems](https://mlsanity.com/paper/2510.13910/) (2025)
- [FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval](https://mlsanity.com/paper/2603.24051/) (2026)
- [Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations](https://mlsanity.com/paper/2604.11322/) (2026)
- [To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents](https://mlsanity.com/paper/2605.18882/) (2026)
- [When Should LLMs Search? Counterfactual Supervision for Search Routing](https://mlsanity.com/paper/2607.05752/) (2026)
- [Therefore I am. I Think](https://mlsanity.com/paper/2604.01202/) (2026)
- [Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning](https://mlsanity.com/paper/2606.00510/) (2026)
- [Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making](https://mlsanity.com/paper/2607.14277/) (2026)
- [OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling](https://mlsanity.com/paper/2608.05141/) (2026)
- [Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling](https://mlsanity.com/paper/2609.00949/) (2026)
- [RRTL: Red Teaming Reasoning Large Language Models in Tool Learning](https://mlsanity.com/paper/2505.17106/) (2025)
- [ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues](https://mlsanity.com/paper/2605.12521/) (2026)
- [Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs](https://mlsanity.com/paper/2605.21027/) (2026)
- [Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments](https://mlsanity.com/paper/2606.03892/) (2026)
- [Strategic Decision Support for AI Agents](https://mlsanity.com/paper/2606.12587/) (2026)
- [SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing](https://mlsanity.com/paper/2607.13594/) (2026)
- [SearchJev: A Fast and Calibrated System-1 Model for Search Agents](https://mlsanity.com/paper/2610.05107/) (2026)
- [AutoAdapt: An Automated Domain Adaptation Framework for LLMs](https://mlsanity.com/paper/2603.08181/) (2026)

## Abstract (arXiv)

Leveraging external tools is a key feature for modern Language Models (LMs) to expand their capabilities and integrate them into existing systems. However, existing benchmarks primarily focus on the accuracy of tool calling -- whether the correct tool is called with the correct parameters -- and less on evaluating when LMs should (not) call tools. We develop a new benchmark, When2Call, which evaluates tool-calling decision-making: when to generate a tool call, when to ask follow-up questions and when to admit the question can't be answered with the tools provided. We find that state-of-the-art tool-calling LMs show significant room for improvement on When2Call, indicating the importance of this benchmark. We also develop a training set for When2Call and leverage the multiple-choice nature of the benchmark to develop a preference optimization training regime, which shows considerably more improvement than traditional fine-tuning. We release the benchmark and training data as well as evaluation scripts at https://github.com/NVIDIA/When2Call.