Extending FunctionGemma for Practical On-Device Mobile Function Calling

arXiv:2609.25373 · cs.LG, cs.SE · Submitted 2026-09-21 · Read on arXiv

cs.LG, cs.SE

Submitted: 2026-09-21

Updated: 2026-09-21

Comments: Accepted at EMNLP 2026. 16 pages, 1 figure, 8 tables. Includes main paper, references, and appendices. Code, datasets, models, and demo available at GitHub and Hugging Face

Code: https://github.com/kivy/plyer

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 34× in this paper · explained in 1 episode
• Fine-Tuning — 21× in this paper · explained in 5 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Quantization — 6× in this paper · explained in 12 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Decode — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Synthetic Data Generation — 2× in this paper · explained in 5 episodes
• Agentic Evaluation — 1× in this paper · explained in 1 episode
• Berkeley Function Calling Leaderboard — 1× in this paper
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformers Reinforcement Learning — 1× in this paper
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• Phi-4 Technical Report
• Qwen Technical Report
• Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling
• Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
• LongFuncEval: Measuring the effectiveness of long context models for function calling
• An LLM Compiler for Parallel Function Calling
• Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
• Gemma: Open Models Based on Gemini Research and Technology
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Decoupled Weight Decay Regularization
• Efficient Guided Generation for Large Language Models
• ReAct: Synergizing Reasoning and Acting in Language Models
• BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks