Cover Image

TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Haque, Mohd Ariful, Rahman, Fahad, Gupta, Kishor Datta, Shujaee, Khalil, George, Roy
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Verbatim Data Transcription Failures in LLM Code Generation: A State-Tracking Stress Test
by: Haque, Mohd Ariful, et al.
Published: (2026)

TinyLLM: A Framework for Training and Deploying Language Models at the Edge Computers
by: Kandala, Savitha Viswanadh, et al.
Published: (2024)

VLCE: A Knowledge-Enhanced Framework for Image Description in Disaster Assessment
by: Rahman, Md. Mahfuzur, et al.
Published: (2025)

Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules
by: Gupta, Kishor Datta, et al.
Published: (2025)

UrbanInsight: A Distributed Edge Computing Framework with LLM-Powered Data Filtering for Smart City Digital Twins
by: Gupta, Kishor Datta, et al.
Published: (2025)

Physics-Based Benchmarking Metrics for Multimodal Synthetic Images
by: Gupta, Kishor Datta, et al.
Published: (2025)

Physical Rule-Guided Convolutional Neural Network
by: Gupta, Kishor Datta, et al.
Published: (2024)

Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM
by: Haque, Mohd Ariful, et al.
Published: (2025)

LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics
by: Williams, Justin, et al.
Published: (2026)

Securing the Diagnosis of Medical Imaging: An In-depth Analysis of AI-Resistant Attacks
by: Nasim, Md Abdullah Al, et al.
Published: (2024)

Continuous Monitoring of Large-Scale Generative AI via Deterministic Knowledge Graph Structures
by: Gupta, Kishor Datta, et al.
Published: (2025)

Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots
by: Williams, Justin, et al.
Published: (2025)

Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models
by: Wu, Yichao, et al.
Published: (2026)

EntroLLM: Entropy Encoded Weight Compression for Efficient Large Language Model Inference on Edge Devices
by: Sanyal, Arnab, et al.
Published: (2025)

Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
by: King, Evan, et al.
Published: (2025)

Grid2Guide: A* Enabled Small Language Model for Indoor Navigation
by: Haque, Md. Wasiul, et al.
Published: (2025)

SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment
by: Haque, Ariful, et al.
Published: (2025)

Securing Radiation Detection Systems with an Efficient TinyML-Based IDS for Edge Devices
by: Pizarro, Einstein Rivas, et al.
Published: (2025)

LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception
by: williams, Justin, et al.
Published: (2026)

Evaluating Time Series Foundation Models on Noisy Periodic Time Series
by: Gupta, Syamantak Datta
Published: (2025)

Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions
by: Naeem, Ashik Abrar, et al.
Published: (2026)

Present and Future of AI in Renewable Energy Domain : A Comprehensive Survey
by: Rashid, Abdur, et al.
Published: (2024)

Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices
by: Suwannaphong, Thanaphon, et al.
Published: (2024)

HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models
by: Sen, Tanmay, et al.
Published: (2024)

TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices
by: Yang, Jianlei, et al.
Published: (2023)

LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection
by: Ocansey, Isaiah Thompson, et al.
Published: (2025)

Agentic Educational Content Generation for African Languages on Edge Devices
by: Gupta, Ravi, et al.
Published: (2025)

Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices
by: Xia, Xiaoyu, et al.
Published: (2024)

TinyAgent: Function Calling at the Edge
by: Erdogan, Lutfi Eren, et al.
Published: (2024)

TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge
by: Fasulo, Matteo, et al.
Published: (2025)

Gradient Extrapolation-Based Policy Optimization
by: Swapnil, Ismam Nur, et al.
Published: (2026)

CUT: Pruning Pre-Trained Multi-Task Models into Compact Models for Edge Devices
by: Zhou, Jingxuan, et al.
Published: (2025)

Tin-Tin: Towards Tiny Learning on Tiny Devices with Integer-based Neural Network Training
by: Hu, Yi, et al.
Published: (2025)

Less is More: Optimizing Function Calling for LLM Execution on Edge Devices
by: Paramanayakam, Varatheepan, et al.
Published: (2024)

Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks
by: Datta, Nirjhor, et al.
Published: (2025)

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
by: Kwon, Young D., et al.
Published: (2023)

Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices
by: Laskar, Md Tahmid Rahman, et al.
Published: (2025)

Safeguarding Privacy in Edge Speech Understanding with Tiny Foundation Models
by: Benazir, Afsara, et al.
Published: (2025)

LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation
by: Sobhan, Shadman, et al.
Published: (2025)

Designing Efficient LLM Accelerators for Edge Devices
by: Haris, Jude, et al.
Published: (2024)