Imagen de Portada

Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sharma, Raghav, Mehta, Manan
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Adaptive and Explainable AI Agents for Anomaly Detection in Critical IoT Infrastructure using LLM-Enhanced Contextual Reasoning
por: Sharma, Raghav, et al.
Publicado: (2025)

RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods
por: Sharma, Raghav, et al.
Publicado: (2025)

ML Compass: Navigating Capability, Cost, and Compliance Trade-offs in AI Model Deployment
por: Digalakis Jr, Vassilis, et al.
Publicado: (2025)

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
por: Gupta, Karan, et al.
Publicado: (2026)

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
por: Chen, Pin-Yu, et al.
Publicado: (2025)

SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment
por: Wang, Jiacheng, et al.
Publicado: (2025)

Emissions and Performance Trade-off Between Small and Large Language Models
por: Garg, Anandita, et al.
Publicado: (2025)

Semantic Text Transmission via Prediction with Small Language Models: Cost-Similarity Trade-off
por: Madhabhavi, Bhavani A, et al.
Publicado: (2024)

Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
por: Ali, Mohamad Abou, et al.
Publicado: (2025)

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment
por: Song, Yixin, et al.
Publicado: (2025)

Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
por: Han, Dongge, et al.
Publicado: (2025)

Alignment For Performance Improvement in Conversation Bots
por: Garg, Raghav, et al.
Publicado: (2024)

Understanding the Quality-Diversity Trade-off in Diffusion Language Models
por: Buzzard, Zak
Publicado: (2025)

Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models
por: Das, Soumi, et al.
Publicado: (2025)

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
por: Liu, Zewen, et al.
Publicado: (2026)

Architectures for Building Agentic AI
por: Nowaczyk, Sławomir
Publicado: (2025)

Small Vision-Language Models: A Survey on Compact Architectures and Techniques
por: Patnaik, Nitesh, et al.
Publicado: (2025)

EffGen: Enabling Small Language Models as Capable Autonomous Agents
por: Srivastava, Gaurav, et al.
Publicado: (2026)

Hymba: A Hybrid-head Architecture for Small Language Models
por: Dong, Xin, et al.
Publicado: (2024)

Small Language Models: Survey, Measurements, and Insights
por: Lu, Zhenyan, et al.
Publicado: (2024)

SAGA: A Security Architecture for Governing AI Agentic Systems
por: Syros, Georgios, et al.
Publicado: (2025)

Quantifying Memorization and Parametric Response Rates in Retrieval-Augmented Vision-Language Models
por: Carragher, Peter, et al.
Publicado: (2025)

An Automated Survey of Generative Artificial Intelligence: Large Language Models, Architectures, Protocols, and Applications
por: Garrido-Merchán, Eduardo C., et al.
Publicado: (2023)

Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques
por: Sharma, Asankhaya
Publicado: (2025)

Trading-off Accuracy and Communication Cost in Federated Learning
por: Villani, Mattia Jacopo, et al.
Publicado: (2025)

Exploring Accuracy-Fairness Trade-off in Large Language Models
por: Zhang, Qingquan, et al.
Publicado: (2024)

IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities
por: Wang, Bin, et al.
Publicado: (2024)

Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment
por: Wang, Xubin, et al.
Publicado: (2025)

Exploring the Adversarial Capabilities of Large Language Models
por: Struppek, Lukas, et al.
Publicado: (2024)

Multimodal Survival Analysis with Locally Deployable Large Language Models
por: Gögl, Moritz, et al.
Publicado: (2026)

Epigraph-Guided Flow Matching for Safe and Performant Offline Reinforcement Learning
por: Tayal, Manan, et al.
Publicado: (2026)

A Comparative Survey of PyTorch vs TensorFlow for Deep Learning: Usability, Performance, and Deployment Trade-offs
por: Alawi, Zakariya Ba
Publicado: (2025)

Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning
por: Ye, Rongguang, et al.
Publicado: (2025)

Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
por: Belgodere, Brian, et al.
Publicado: (2023)

Environment Scaling for Interactive Agentic Experience Collection: A Survey
por: Huang, Yuchen, et al.
Publicado: (2025)

PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training
por: Yi, Rongjie, et al.
Publicado: (2024)

MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency
por: Liu, Xiaoyun, et al.
Publicado: (2023)

Geometric Dynamics of Agentic Loops in Large Language Models
por: Tacheny, Nicolas
Publicado: (2025)

From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks
por: Geng, Xue, et al.
Publicado: (2024)

A Small Math Model: Recasting Strategy Choice Theory in an LLM-Inspired Architecture
por: Rahman, Roussel, et al.
Publicado: (2025)