{"total":24,"rows":[{"id":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2606.30560","title":"TraceLab: Characterizing Coding Agent Workloads for LLM Serving","created":"2026-06-29","cited_by_count":16,"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":"2603.04428","title":"Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices","created":"2026-02-17","cited_by_count":8,"area":"agents"},{"id":"2603.13281","title":"ICaRus: Identical Cache Reuse for Efficient Multi Model Inference","created":"2026-02-27","cited_by_count":8,"area":"agents"},{"id":"2604.13349","title":"When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration","created":"2026-04-14","cited_by_count":5,"area":"agents"},{"id":"2605.30842","title":"CoMem: Context Management with A Decoupled Long-Context Model","created":"2026-05-29","cited_by_count":5,"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":"2607.08032","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","created":"2026-07-09","cited_by_count":4,"area":"agents"},{"id":"2510.05059","title":"Staircase Streaming for Low-Latency Multi-Agent Inference","created":"2025-10-06","cited_by_count":3,"area":"agents"},{"id":"2604.24971","title":"PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference","created":"2026-04-27","cited_by_count":3,"area":"agents"},{"id":"2605.17170","title":"TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2607.08565","title":"SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling","created":"2026-07-09","cited_by_count":2,"area":"agents"},{"id":"2607.28069","title":"SemPIC: Learning Semantic Position-Independent KV Caches","created":"2026-07-30","cited_by_count":2,"area":"agents"},{"id":"2604.10235","title":"CodeComp: Structural KV Cache Compression for Agentic Coding","created":"2026-04-11","cited_by_count":1,"area":"agents"},{"id":"2605.03884","title":"QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs","created":"2026-05-05","cited_by_count":1,"area":"agents"},{"id":"2605.30102","title":"When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"id":"2608.06557","title":"Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving","created":"2026-08-06","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":"2606.25532","title":"Agentic evolution of physically constrained foundation models","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2608.15117","title":"Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads","created":"2026-08-15","cited_by_count":0,"area":"agents"},{"id":"2609.26219","title":"PatchKV: Efficient KV Cache Recovery for Dynamically Edited LLM Contexts","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2609.35427","title":"LLMs are General Asynchronous Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}