PulseAugur
EN
LIVE 16:50:02

FunctionGemma extended for on-device mobile function calling

By PulseAugur Editorial · [1 sources] ·

Researchers have extended Google's FunctionGemma model to improve on-device mobile function calling capabilities. They introduced a new dataset, MOBILEACTIONSEXTENDED, containing approximately 9,500 conversations across fifteen device-control categories. Fine-tuning the FunctionGemma 270M model on this dataset significantly boosted end-to-end accuracy to 76.5%, a substantial improvement over the base model and Google's existing Mobile-Actions variant. This work highlights the potential for compact, local function calling to enable low-latency and privacy-preserving mobile assistants. AI

IMPACT Enhances on-device AI capabilities, potentially leading to more responsive and private mobile assistants.

RANK_REASON The cluster describes a research paper detailing an extension to an existing model (FunctionGemma) with a new dataset and fine-tuning methodology for a specific application (on-device mobile function calling). [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

FunctionGemma extended for on-device mobile function calling

How we ranked this

Signal score
5 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a research paper detailing an extension to an existing model (FunctionGemma) with a new dataset and fine-tuning methodology for a specific application (on-device mobile functi…
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Ali Rezagholizadeh, Soheila Samiee ·

    Extending FunctionGemma for Practical On-Device Mobile Function Calling

    arXiv:2609.25373v2 Announce Type: replace Abstract: On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or narrow mobile-action catalogs. We extend FunctionGemma 270M-it to practical And…

RELATED ENTITIES

RELATED TOPICS