{"total":88,"rows":[{"id":"2601.02163","title":"EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning","created":"2026-01-05","cited_by_count":54,"area":"lr"},{"id":"2605.12493","title":"LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues","created":"2026-05-12","cited_by_count":23,"area":"agents"},{"id":"2601.13722","title":"OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents","created":"2026-01-20","cited_by_count":22,"area":"agents"},{"id":"2602.01313","title":"Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues","created":"2026-02-01","cited_by_count":22,"area":null},{"id":"2601.06966","title":"RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction","created":"2026-01-11","cited_by_count":20,"area":null},{"id":"2604.17283","title":"HorizonBench: Long-Horizon Personalization with Evolving Preferences","created":"2026-04-19","cited_by_count":17,"area":null},{"id":"2605.14498","title":"GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations","created":"2026-05-14","cited_by_count":17,"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":"2602.22680","title":"Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions","created":"2026-02-26","cited_by_count":14,"area":"agents"},{"id":"2603.23231","title":"PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2605.12357","title":"$\\delta$-mem: Efficient Online Memory for Large Language Models","created":"2026-05-12","cited_by_count":13,"area":null},{"id":"2602.11243","title":"Evaluating Memory Structure in LLM Agents","created":"2026-02-11","cited_by_count":12,"area":"rag"},{"id":"2605.27141","title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","created":"2026-05-26","cited_by_count":12,"area":"agents"},{"id":"2607.01071","title":"MemSyco-Bench: Benchmarking Sycophancy in Agent Memory","created":"2026-07-01","cited_by_count":12,"area":"agents"},{"id":"2603.26680","title":"AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment","created":"2026-03-09","cited_by_count":10,"area":null},{"id":"2601.18572","title":"One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization","created":"2026-01-26","cited_by_count":9,"area":null},{"id":"2606.13681","title":"EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments","created":"2026-06-11","cited_by_count":9,"area":"agents"},{"id":"2603.28590","title":"MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models","created":"2026-03-30","cited_by_count":8,"area":"lr"},{"id":"2601.17887","title":"When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents","created":"2026-01-25","cited_by_count":7,"area":"agents"},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2605.09530","title":"MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents","created":"2026-05-10","cited_by_count":7,"area":"agents"},{"id":"2606.05622","title":"AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints","created":"2026-06-04","cited_by_count":7,"area":"agents"},{"id":"2608.04205","title":"MatrAIx: Simulating the World with 8.3 Billion Persona Agents","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2606.24595","title":"MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery","created":"2026-06-23","cited_by_count":6,"area":"agents"},{"id":"2606.23459","title":"TriggerBench: Investigating Prospective Memory for Large Language Models","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2602.12394","title":"Synthetic Interaction Data for Scalable Personalization in Large Language Models","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2605.30690","title":"ElasticMem: Latent Memory as a Learnable Resource for LLM Agents","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2606.22877","title":"DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settings","created":"2026-06-22","cited_by_count":4,"area":"agents"},{"id":"2601.01530","title":"EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World","created":"2026-01-04","cited_by_count":3,"area":null},{"id":"2603.20939","title":"User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction","created":"2026-03-21","cited_by_count":3,"area":"rag"},{"id":"2606.16100","title":"Your \"Pro\" LLM Subscription May Actually Be \"Free\": Exposing Fingerprint Spoofing Risks in LLM Inference Services","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2606.19172","title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2607.18975","title":"Mi-Memory: A Lifecycle Memory Framework for Personal AI","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2601.11969","title":"MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models","created":"2026-01-17","cited_by_count":2,"area":"alignment"},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2604.04373","title":"Decocted Experience Improves Test-Time Inference in LLM Agents","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2604.11610","title":"Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks","created":"2026-04-13","cited_by_count":2,"area":"synth"},{"id":"2604.17886","title":"Latent Preference Modeling for Multi-Session Personalized Tool Calling","created":"2026-04-20","cited_by_count":2,"area":"agents"},{"id":"2605.11814","title":"MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.14177","title":"Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2605.28806","title":"Personal Visual Memory from Explicit and Implicit Evidence","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.09483","title":"Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents","created":"2026-06-08","cited_by_count":2,"area":"agents"},{"id":"2607.05794","title":"From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2607.28818","title":"Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2609.03467","title":"When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents","created":"2026-09-03","cited_by_count":2,"area":"agents"},{"id":"2601.10809","title":"A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents","created":"2026-01-15","cited_by_count":1,"area":"agents"},{"id":"2603.01059","title":"GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant","created":"2026-03-01","cited_by_count":1,"area":"agents"},{"id":"2603.15642","title":"CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems","created":"2026-03-03","cited_by_count":1,"area":"agents"},{"id":"2605.07799","title":"Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.09996","title":"Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization","created":"2026-05-11","cited_by_count":1,"area":"mllm"},{"id":"2605.25758","title":"StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.28773","title":"Rethinking Memory as Continuously Evolving Connectivity","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.04660","title":"LifeSide: Benchmarking Agents as Lifelong Digital Companions","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.05761","title":"SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.10428","title":"Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2608.04570","title":"The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.11879","title":"Total Recall at What Cost? Benchmarking the Serving Cost of Agentic Memory Systems","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2608.13606","title":"MobileMem: Learning from a Year of Mobile Experiences","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.00570","title":"VoiceLongMemEval: Do Assistants Remember How You Sounded?","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.15972","title":"Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2609.18461","title":"Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning","created":"2026-09-16","cited_by_count":1,"area":"lr"},{"id":"2609.23466","title":"RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents","created":"2026-09-20","cited_by_count":1,"area":"agents"},{"id":"2601.05107","title":"Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction","created":"2026-01-08","cited_by_count":0,"area":"agents"},{"id":"2606.02754","title":"$\\Psi$-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.26654","title":"SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.02374","title":"DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.20471","title":"Benchmarking the Personalization Capabilities of Large Language Models","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.27056","title":"Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2607.29433","title":"Know It, Act on It: Investigating Memory Utilization in LLM Personalization","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.02613","title":"MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale","created":"2026-05-20","cited_by_count":0,"area":"agents"},{"id":"2608.09507","title":"Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.21381","title":"PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2609.00921","title":"VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.03293","title":"PACE: Towards Surfacing Hidden Conflicts in User Requests","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.03815","title":"Inferring Hidden User Models from the Behavior of Personalized LLM Agents","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"id":"2609.08558","title":"Personalizing LLM Agent Memory Using Biometrics","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.08599","title":"Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.09778","title":"ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"id":"2609.09835","title":"HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization","created":"2026-09-09","cited_by_count":0,"area":"alignment"},{"id":"2609.17010","title":"ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19167","title":"To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.33182","title":"Unlocking Latent Personalization in LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36722","title":"ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.01780","title":"RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.11573","title":"Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.11776","title":"DPPM: Dual-Path Parametric Memory for Personalized Language Models","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14952","title":"Do Personalized LLMs Need the Whole Conversation? Matching the Full History with Only 5% of Its Text via Relevance-Filtered Context","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}