# Hammer: Robust Function-Calling for On-Device Language Models via Function Masking

arXiv: https://arxiv.org/abs/2410.04587 · HTML: https://mlsanity.com/paper/2410.04587/

## Key facts

- Cited by 55 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 27 references that are in the map.
- First posted on arXiv 6 Oct 2024.

## 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)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [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)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [xLAM: A Family of Large Action Models to Empower AI Agent Systems](https://mlsanity.com/paper/2409.03215/) (2024)
- [Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark](https://mlsanity.com/paper/2405.08355/) (2024)
- [TinyAgent: Function Calling at the Edge](https://mlsanity.com/paper/2409.00608/) (2024)
- [Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks](https://mlsanity.com/paper/2407.00121/) (2024)
- [API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs](https://mlsanity.com/paper/2402.15491/) (2024)
- [Octopus: On-device language model for function calling of software APIs](https://mlsanity.com/paper/2404.01549/) (2024)
- [Reinforcing Language Agents via Policy Optimization with Action Decomposition](https://mlsanity.com/paper/2405.15821/) (2024)

## Built on by (most cited first, 30 of 55)

- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [ACEBench: Who Wins the Match Point in Tool Usage?](https://mlsanity.com/paper/2501.12851/) (2025)
- [Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation](https://mlsanity.com/paper/2503.07826/) (2025)
- [MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use](https://mlsanity.com/paper/2508.18669/) (2025)
- [Rethinking On-Policy Distillation of Large Language Models II: One Training Example](https://mlsanity.com/paper/2609.04172/) (2026)
- [LLM-based Multi-Agent Systems: Techniques and Business Perspectives](https://mlsanity.com/paper/2411.14033/) (2024)
- [Agentic Information Retrieval](https://mlsanity.com/paper/2410.09713/) (2024)
- [Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model](https://mlsanity.com/paper/2502.08820/) (2025)
- [Tool Preferences in Agentic LLMs are Unreliable](https://mlsanity.com/paper/2505.18135/) (2025)
- [ToolRM: Outcome Reward Models for Tool-Calling Large Language Models](https://mlsanity.com/paper/2509.11963/) (2025)
- [Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch](https://mlsanity.com/paper/2511.01934/) (2025)
- [Benchmarking LLM Tool-Use in the Wild](https://mlsanity.com/paper/2604.06185/) (2026)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions](https://mlsanity.com/paper/2504.02623/) (2025)
- [Automating High Energy Physics Data Analysis with LLM-Powered Agents](https://mlsanity.com/paper/2512.07785/) (2025)
- [ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning](https://mlsanity.com/paper/2504.01400/) (2025)
- [TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation](https://mlsanity.com/paper/2505.20016/) (2025)
- [iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use](https://mlsanity.com/paper/2501.09766/) (2025)
- [ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution](https://mlsanity.com/paper/2505.07512/) (2025)
- [Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists](https://mlsanity.com/paper/2506.00042/) (2025)
- [C3-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking](https://mlsanity.com/paper/2505.18746/) (2025)
- [ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"](https://mlsanity.com/paper/2508.04086/) (2025)
- [Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories](https://mlsanity.com/paper/2607.10601/) (2026)
- [MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models](https://mlsanity.com/paper/2507.00487/) (2025)
- [LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval](https://mlsanity.com/paper/2508.07690/) (2025)
- [ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning](https://mlsanity.com/paper/2509.14718/) (2025)
- [AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems](https://mlsanity.com/paper/2510.00229/) (2025)
- [DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning](https://mlsanity.com/paper/2605.25604/) (2026)

## Abstract (arXiv)

Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls. Nonetheless, effectively harnessing their potential for executing complex tasks crucially relies on enhancements in their function calling capabilities. This paper identifies a critical gap in existing function calling models, where performance varies significantly across benchmarks, often due to being misled by specific naming conventions. To address such an issue, we introduce Hammer, a novel family of foundation models specifically engineered for on-device function calling. Hammer employs an augmented dataset that enhances models' sensitivity to irrelevant functions and incorporates function masking techniques to minimize misleading. Our empirical evaluations reveal that Hammer not only outperforms larger models but also demonstrates robust generalization across diverse benchmarks, achieving sota results. Our open source contributions include a specialized dataset for irrelevance detection, a tuning framework for enhanced generalization, and the Hammer models, establishing a new standard for function calling performance.