{"total":41,"rows":[{"id":"2507.07957","title":"MIRIX: Multi-Agent Memory System for LLM-Based Agents","created":"2025-07-10","cited_by_count":173,"area":"agents"},{"id":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44,"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":"2606.23525","title":"Self-Compacting Language Model Agents","created":"2026-06-22","cited_by_count":11,"area":"agents"},{"id":"2607.00692","title":"Self-GC: Self-Governing Context for Long-Horizon LLM Agents","created":"2026-07-01","cited_by_count":11,"area":"agents"},{"id":"2605.08580","title":"Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents","created":"2026-05-09","cited_by_count":6,"area":"agents"},{"id":"2606.09916","title":"IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference","created":"2026-06-06","cited_by_count":6,"area":"agents"},{"id":"2606.01065","title":"Leyline: KV Cache Directives for Agentic Inference","created":"2026-05-31","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":"2606.20954","title":"Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning","created":"2026-06-18","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":"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":"2607.10582","title":"MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference","created":"2026-07-12","cited_by_count":3,"area":"agents"},{"id":"2608.20617","title":"Dual-Cache Latent Space Communication between Heterogeneous Language Models","created":"2026-08-20","cited_by_count":3,"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":"2607.28069","title":"SemPIC: Learning Semantic Position-Independent KV Caches","created":"2026-07-30","cited_by_count":2,"area":"agents"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","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":"2606.06453","title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","created":"2026-06-04","cited_by_count":1,"area":"agents"},{"id":"2606.23961","title":"Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets","created":"2026-06-22","cited_by_count":1,"area":"agents"},{"id":"2608.15008","title":"Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents","created":"2026-08-15","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":"2609.27298","title":"StateComp: Learning When to Compress History in Long Horizon Agents","created":"2026-09-23","cited_by_count":1,"area":"agents"},{"id":"2604.08603","title":"From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2608.22577","title":"CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI Agents","created":"2026-08-23","cited_by_count":0,"area":"agents"},{"id":"2609.14872","title":"AgentKV: Phase-Aware KV Eviction for Agentic LLMs","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.20734","title":"On-Demand Attention: Language Models Know When to Recall","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.22158","title":"StepKV: Step-Aware KV Cache Compression for LLM Agents","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.23790","title":"Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows","created":"2026-09-20","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":"2609.30797","title":"HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.31395","title":"ActKV: Efficient LLM Agents through Action-Guided KV Cache Management","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.31568","title":"DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.37017","title":"LatCom: Cross-Agent Latent Compression for Efficient Multi-Agent Collaboration","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.37590","title":"FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39068","title":"SparseEngine: Sparse-First Inference Engine","created":"2026-09-30","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"},{"id":"2610.02404","title":"Trained Agentic Context Management","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.19822","title":"JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}