{"total":21,"rows":[{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2602.06025","title":"Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory","created":"2026-02-05","cited_by_count":13,"area":"agents"},{"id":"2506.24045","title":"Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC","created":"2025-06-30","cited_by_count":11,"area":"agents"},{"id":"2505.19481","title":"Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs","created":"2025-05-26","cited_by_count":9,"area":"agents"},{"id":"2609.20519","title":"SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness","created":"2026-09-17","cited_by_count":5,"area":"agents"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2603.08727","title":"ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs","created":"2026-02-19","cited_by_count":4,"area":"agents"},{"id":"2605.20315","title":"Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs","created":"2026-05-19","cited_by_count":4,"area":"agents"},{"id":"2505.22311","title":"From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications","created":"2025-05-28","cited_by_count":2,"area":"agents"},{"id":"2601.09694","title":"LLMs can Compress LLMs: Adaptive Pruning by Agents","created":"2026-01-14","cited_by_count":2,"area":"agents"},{"id":"2508.18177","title":"Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance","created":"2025-08-25","cited_by_count":1,"area":"agents"},{"id":"2601.05191","title":"AgentCompress: Task-Aware Compression for Affordable Large Language Model Agents","created":"2026-01-08","cited_by_count":1,"area":"agents"},{"id":"2605.08813","title":"AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2607.13080","title":"Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs","created":"2026-07-13","cited_by_count":1,"area":"agents"},{"id":"2607.28196","title":"Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.07915","title":"SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2604.13206","title":"Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models","created":"2026-04-14","cited_by_count":0,"area":"agents"},{"id":"2606.25532","title":"Agentic evolution of physically constrained foundation models","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2610.19382","title":"ixi-sLM: On-Device sLM for AI Call Agent Service","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}