{"total":36,"rows":[{"id":"2507.05257","title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","created":"2025-07-07","cited_by_count":254,"area":"agents"},{"id":"2602.16313","title":"MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks","created":"2026-02-18","cited_by_count":84,"area":"agents"},{"id":"2604.20006","title":"From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents","created":"2026-04-21","cited_by_count":36,"area":"agents"},{"id":"2603.03296","title":"PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents","created":"2026-02-06","cited_by_count":32,"area":"agents"},{"id":"2603.01045","title":"Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2511.13998","title":"LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering","created":"2025-11-17","cited_by_count":16,"area":"agents"},{"id":"2603.04814","title":"Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents","created":"2026-03-05","cited_by_count":15,"area":"agents"},{"id":"2510.01353","title":"MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments","created":"2025-10-01","cited_by_count":13,"area":"agents"},{"id":"2502.15920","title":"Self-Taught Agentic Long Context Understanding","created":"2025-02-21","cited_by_count":10,"area":"agents"},{"id":"2601.12910","title":"SciCoQA: Quality Assurance for Scientific Paper--Code Alignment","created":"2026-01-19","cited_by_count":10,"area":"agents"},{"id":"2601.20730","title":"AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts","created":"2026-01-28","cited_by_count":9,"area":"agents"},{"id":"2601.08435","title":"Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"id":"2505.20625","title":"Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration","created":"2025-05-27","cited_by_count":7,"area":"agents"},{"id":"2605.17641","title":"Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents","created":"2026-05-17","cited_by_count":6,"area":"agents"},{"id":"2606.25161","title":"TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory","created":"2026-06-23","cited_by_count":6,"area":"agents"},{"id":"2511.04064","title":"Benchmarking and Studying the LLM-based Agent System in End-to-End Software Development","created":"2025-11-06","cited_by_count":5,"area":"agents"},{"id":"2602.03128","title":"Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance","created":"2026-02-03","cited_by_count":5,"area":"agents"},{"id":"2505.21471","title":"Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration","created":"2025-05-27","cited_by_count":4,"area":"agents"},{"id":"2510.07414","title":"Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"id":"2606.17328","title":"MemTrace: Probing What Final Accuracy Misses in Long-Term Memory","created":"2026-06-15","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":"2505.03973","title":"Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale","created":"2025-05-06","cited_by_count":3,"area":"agents"},{"id":"2604.26963","title":"MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems","created":"2026-04-14","cited_by_count":3,"area":"agents"},{"id":"2505.02709","title":"Technical Report: Evaluating Goal Drift in Language Model Agents","created":"2025-05-05","cited_by_count":2,"area":"agents"},{"id":"2603.02631","title":"Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models","created":"2026-03-03","cited_by_count":2,"area":"agents"},{"id":"2608.01285","title":"Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents","created":"2026-08-02","cited_by_count":2,"area":"agents"},{"id":"2608.28476","title":"ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL","created":"2026-08-28","cited_by_count":2,"area":"agents"},{"id":"2603.25770","title":"ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation","created":"2026-03-26","cited_by_count":1,"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":"2605.27240","title":"ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2608.12888","title":"When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory","created":"2026-08-13","cited_by_count":1,"area":"agents"},{"id":"2606.25361","title":"Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2608.26263","title":"SKILL.state: Scalable Long-Horizon Agent Skills","created":"2026-08-26","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":"2609.32658","title":"Contract Memory Compiler: Resolve, Then Traverse","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.18052","title":"Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}