{"total":20,"rows":[{"id":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109,"area":"agents"},{"id":"2502.17421","title":"LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification","created":"2025-02-24","cited_by_count":21,"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":"2509.01920","title":"Dynamic Speculative Agent Planning","created":"2025-09-02","cited_by_count":12,"area":"agents"},{"id":"2607.03333","title":"SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference","created":"2026-07-03","cited_by_count":6,"area":"agents"},{"id":"2605.10380","title":"Agent-X: Full Pipeline Acceleration of On-device AI Agents","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2607.17299","title":"WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning","created":"2026-07-19","cited_by_count":3,"area":"agents"},{"id":"2606.31023","title":"Certified Speculative Execution for Untrusted AI Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2608.00814","title":"OoO-Spec: Out-of-Order Semantic Speculation for Fast Tool Calling","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.15763","title":"Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report","created":"2026-08-16","cited_by_count":1,"area":"agents"},{"id":"2608.26004","title":"AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2610.07086","title":"SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding","created":"2026-10-05","cited_by_count":1,"area":"agents"},{"id":"2604.19767","title":"Accelerating PayPal's Commerce Agent with Speculative Decoding: An Empirical Study on EAGLE3 with Fine-Tuned Nemotron Models","created":"2026-03-27","cited_by_count":0,"area":"agents"},{"id":"2606.18502","title":"Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications","created":"2026-06-16","cited_by_count":0,"area":"agents"},{"id":"2607.20507","title":"CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models","created":"2026-07-03","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":"2609.18123","title":"AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines","created":"2026-09-16","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"},{"id":"2610.02670","title":"LEAP: Learning Efficient Action Proposals For LLM Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.17436","title":"SchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}