Cover Image

Efficient On-Device Agents via Adaptive Context Management

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vijayvargiya, Sanidhya, Lokesh, Rahul
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks
by: Vijayvargiya, Sanidhya, et al.
Published: (2026)

Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering
by: Vijayvargiya, Sanidhya, et al.
Published: (2025)

Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
by: Ning, Yansong, et al.
Published: (2026)

Causal Contextual Bandits with Adaptive Context
by: Madhavan, Rahul, et al.
Published: (2024)

Neural Paging: Learning Context Management Policies for Turing-Complete Agents
by: Chen, Liang, et al.
Published: (2026)

RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference
by: Gautam, Arpit Singh, et al.
Published: (2026)

Bandit Guided Submodular Curriculum for Adaptive Subset Selection
by: Chanda, Prateek, et al.
Published: (2025)

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
by: Vijayvargiya, Sanidhya, et al.
Published: (2025)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
by: Ye, Rui, et al.
Published: (2025)

FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents
by: Shao, Jiaqi, et al.
Published: (2025)

Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces
by: Kar, Avik, et al.
Published: (2024)

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
by: Yang, Xinyu, et al.
Published: (2025)

Efficient Graph Understanding with LLMs via Structured Context Injection
by: Waghmare, Govind, et al.
Published: (2025)

Context Distillation as Latent Memory Management
by: Zheng, Ziyang, et al.
Published: (2026)

Training Long-Context LLMs Efficiently via Chunk-wise Optimization
by: Li, Wenhao, et al.
Published: (2025)

Efficient and Adaptive Human Activity Recognition via LLM Backbones
by: Bredikhin, Aleksandr, et al.
Published: (2026)

AdaProb: Efficient Machine Unlearning via Adaptive Probability
by: Zhao, Zihao, et al.
Published: (2024)

ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization
by: Su, Hongyuan, et al.
Published: (2026)

MEMENTO: Teaching LLMs to Manage Their Own Context
by: Kontonis, Vasilis, et al.
Published: (2026)

GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search
by: Zhou, Ao, et al.
Published: (2025)

Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning
by: Chen, Xi, et al.
Published: (2025)

Reliable Self-Harm Risk Screening via Adaptive Multi-Agent LLM Systems
by: Karnam, Meghana, et al.
Published: (2026)

Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
by: Kadiyala, Lokesh Antony, et al.
Published: (2025)

Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
by: Joo, Taejong, et al.
Published: (2025)

SmartBench: Evaluating LLMs in Smart Homes with Anomalous Device States and Behavioral Contexts
by: Zou, Qingsong, et al.
Published: (2026)

EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness
by: Zhang, Yunxiao, et al.
Published: (2025)

Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insights
by: Wang, Yuan, et al.
Published: (2024)

Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Models
by: Wen, Ziting, et al.
Published: (2024)

AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems
by: Kadekodi, Rohan, et al.
Published: (2025)

Mathematical Framework for Custom Reward Functions in Job Application Evaluation using Reinforcement Learning
by: Jain, Shreyansh, et al.
Published: (2025)

In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks
by: Dennis, Simon, et al.
Published: (2026)

NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networks
by: Johnsen, Tim, et al.
Published: (2024)

GR-Agent: Adaptive Graph Reasoning Agent under Incomplete Knowledge
by: Zhou, Dongzhuoran, et al.
Published: (2025)

TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
by: Meng, Xiang, et al.
Published: (2025)

ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference
by: Liu, Xiao, et al.
Published: (2025)

Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning
by: Zhang, Dingwen, et al.
Published: (2024)

Fine-Tuned In-Context Learners for Efficient Adaptation
by: Bornschein, Jorg, et al.
Published: (2025)

CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
by: Yang, Zi, et al.
Published: (2024)

SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices
by: Zhong, Zhengyi, et al.
Published: (2025)

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
by: Jia, Yongzhe, et al.
Published: (2024)