{"total":16,"rows":[{"id":"2507.07400","title":"KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows","created":"2025-07-10","cited_by_count":56,"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":"2512.15834","title":"Optimizing Agentic Language Model Inference via Speculative Tool Calls","created":"2025-12-17","cited_by_count":13,"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":"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":"2608.10402","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","created":"2026-08-11","cited_by_count":4,"area":"agents"},{"id":"2606.01839","title":"Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving","created":"2026-06-01","cited_by_count":2,"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":"2608.25523","title":"TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2604.17353","title":"Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2608.20566","title":"AgentDecarbonizer: Carbon-Aware Execution for AI Agents","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2608.24650","title":"Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.18849","title":"Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.32256","title":"LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33762","title":"EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents?","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.40118","title":"Persistent Context Graphs for Efficient Memory Compaction in LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}