mlsanityData to 14 Oct 2026

PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory

arXiv 2512.06688 ↗First posted 7 Dec 2025cs.CLcited by 88

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simulates 1,000 realistic user-chatbot interactions on 300+ scenarios, 20,000+ user preferences, and 128k-token context windows, where most user preferences are implicitly revealed to reflect real-world interactions. Using this data, we investigate how reinforcement fine-tuning enables a model to improve its long-context reasoning capabilities for user understanding and personalization. We also develop a framework for training an agentic memory system, which maintains a single, human-readable memory that grows with each user over time. In our experiments, frontier LLMs still struggle with implicit personalization, achieving only 37-48% accuracy. While they support long context windows, reasoning remains the bottleneck for implicit personalization tasks. Using reinforcement fine-tuning, we successfully train Qwen3-4B to outperforms GPT-5, reaching 53% accuracy in implicit personalization. Moreover, our agentic memory framework achieves state-of-the-art 55% accuracy while using 16x fewer input tokens, relying on a 2k-token memory instead of full 32k conversation histories. These results underscore the impact of our dataset and demonstrate agentic memory as a scalable path toward real-world personalized intelligence.

Key facts. Cited by 88 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 54 of its 61 references that are in the map. First posted on arXiv 7 Dec 2025.

Builds on

54 of 61 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
  2. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  3. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  4. 2024Large Language Models Empowered Personalized Web Agents22 Oct
  5. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs28 Sep
  6. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialogue9 Jun
  7. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  8. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 46

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  8. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  9. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  10. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  11. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  12. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
34 more
  1. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  2. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 417
  3. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 246
  4. 2025Inference-Time Scaling for Generalist Reward Modelingcited by 239
  5. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  6. 2024Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Datacited by 185
  7. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
  8. 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 148
  9. 2024Personalized Language Modeling from Personalized Human Feedbackcited by 132
  10. 2024Personalization of Large Language Models: A Surveycited by 104
  11. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelscited by 73
  12. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 71
  13. 2024PersonalLLM: Tailoring LLMs to Individual Preferencescited by 60
  14. 2025Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Searchcited by 53
  15. 2024RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Modelscited by 48
  16. 2025Sleep-time Compute: Beyond Inference Scaling at Test-timecited by 43
  17. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 42
  18. 2025RL Tango: Reinforcing Generator and Verifier Together for Language Reasoningcited by 40
  19. 2024WildFeedback: Aligning LLMs With In-situ User Interactions And Feedbackcited by 31
  20. 2024PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agentscited by 30
  21. 2025PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Processcited by 18
  22. 2024WildfireGPT: Tailored Large Language Model for Wildfire Analysiscited by 15
  23. 2025Personalized LLM Decoding via Contrasting Personal Preferencecited by 12
  24. 2025ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendationcited by 12
  25. 2025Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrievalcited by 11
  26. 2023Exploring ChatGPT's Empathic Abilitiescited by 10
  27. 2024Generative AI in Education: A Study of Educators' Awareness, Sentiments, and Influencing Factorscited by 10
  28. 2025Memory Assisted LLM for Personalized Recommendation Systemcited by 9
  29. 2025MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMscited by 9
  30. 2025REMI: A Novel Causal Schema Memory Architecture for Personalized Lifestyle Recommendation Agentscited by 4
  31. 2025Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graphcited by 3
  32. 2025Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learningcited by 3
  33. 2020Artificial intelligence in medicine and healthcare: a review and classification of current and near-future applications and their ethical and social Impactcited by 2
  34. 2022AI Approaches in Processing and Using Data in Personalized Medicinecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 88.

88 papers.

Sort:

By area:

  1. 2026EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoningcited by 54
  2. 2026LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleaguescited by 23
  3. 2026OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agentscited by 22
  4. 2026Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialoguescited by 22
  5. 2026RealMem: Benchmarking LLMs in Real-World Memory-Driven Interactioncited by 20
  6. 2026HorizonBench: Long-Horizon Personalization with Evolving Preferencescited by 17
  7. 2026GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversationscited by 17
  8. 2026Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agentscited by 15
  9. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 14
  10. 2026PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environmentscited by 14
  11. 2026δ-mem: Efficient Online Memory for Large Language Modelscited by 13
  12. 2026Evaluating Memory Structure in LLM Agentscited by 12
38 more
  1. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 12
  2. 2026MemSyco-Bench: Benchmarking Sycophancy in Agent Memorycited by 12
  3. 2026AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignmentcited by 10
  4. 2026One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalizationcited by 9
  5. 2026EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environmentscited by 9
  6. 2026MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Modelscited by 8
  7. 2026When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agentscited by 7
  8. 2026One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligencecited by 7
  9. 2026MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agentscited by 7
  10. 2026AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraintscited by 7
  11. 2026MatrAIx: Simulating the World with 8.3 Billion Persona Agentscited by 7
  12. 2026MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systemscited by 6
  13. 2026MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recoverycited by 6
  14. 2026TriggerBench: Investigating Prospective Memory for Large Language Modelscited by 5
  15. 2026Synthetic Interaction Data for Scalable Personalization in Large Language Modelscited by 4
  16. 2026ElasticMem: Latent Memory as a Learnable Resource for LLM Agentscited by 4
  17. 2026DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settingscited by 4
  18. 2026EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal Worldcited by 3
  19. 2026User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interactioncited by 3
  20. 2026Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Servicescited by 3
  21. 2026User as Engram: Internalizing Per-User Memory as Local Parametric Editscited by 3
  22. 2026Mi-Memory: A Lifecycle Memory Framework for Personal AIcited by 3
  23. 2026MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Modelscited by 2
  24. 2026Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimizationcited by 2
  25. 2026Decocted Experience Improves Test-Time Inference in LLM Agentscited by 2
  26. 2026Self-Evolving LLM Memory Extraction Across Heterogeneous Taskscited by 2
  27. 2026Latent Preference Modeling for Multi-Session Personalized Tool Callingcited by 2
  28. 2026MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcarecited by 2
  29. 2026Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Modelscited by 2
  30. 2026Personal Visual Memory from Explicit and Implicit Evidencecited by 2
  31. 2026Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agentscited by 2
  32. 2026From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Spacecited by 2
  33. 2026Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companionscited by 2
  34. 2026When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agentscited by 2
  35. 2026A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agentscited by 1
  36. 2026GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistantcited by 1
  37. 2026CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systemscited by 1
  38. 2026Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learningcited by 1

50 most cited of 88 All 88 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025PersonaAgent: Bridging Memory and Action for Personalized LLM Agents
  2. 2026DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
  3. 2025SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs
  4. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
  5. 2025HumAIne-Chatbot: Real-Time Personalized Conversational AI via Reinforcement Learning
  6. 2026Learning Personalized Agents from Human Feedback
  7. 2025Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
  8. 2026PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents