mlsanityData to 14 Oct 2026

PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks

arXiv 2608.21381 ↗First posted 16 Jul 2026cs.CY cs.CLcited by 0

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

Abstract (arXiv)

Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across the digital contexts where their preferences, intents, habits, social relationships, and needs unfold over time. Today's systems can personalize within individual apps or tasks, but personal intelligence as a whole remains under-measured: how agents build cross-context user understanding, support steerable recommendation systems, act proactively across platforms, and avoid over-personalization. We introduce PersonaMem-v3, a real-world-grounded benchmark and evaluation harness for omni-platform personal intelligence. PersonaMem-v3 is seeded from more than one million anonymized real-world engagement histories, most of which are implicit signals, and uses them to construct time-indexed user digital worlds across social media, chatbot, calendar, and AI-companion with preference evolvement over time. The benchmark brings personalization, LLM-powered recommendation, proactiveness, agentic tool use, and geo-temporal reasoning into one framework, anchored in psychology, social-linguistics, and user-behavior theories. It evaluates whether AI agents can infer holistic user understanding from cross-platform evidence, personalize responses, rerank recommendations on social media, follow user steering through natural language, and hold back when personalization would be inappropriate, repetitive, outdated, or unnecessary. PersonaMem-v3 points toward LLM-powered personal intelligent agents that work with existing scalable recommendation infrastructure while making personalization more interactive, agentic, and aligned with how real users experience their digital lives.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 57 of its 99 references that are in the map. First posted on arXiv 16 Jul 2026.

Builds on

57 of 99 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective18 May
  2. 2026OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents20 Jan
  3. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory7 Dec
  4. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory25 Nov
  5. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory29 Sep
  6. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning27 Aug
  7. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agents10 Jul
  8. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  9. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  10. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  11. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 46

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  3. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  4. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  5. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 379
  6. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  7. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 309
  8. 2024Long-context LLMs Struggle with Long In-context Learningcited by 286
  9. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 246
  10. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  11. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
  12. 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 148
34 more
  1. 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)cited by 141
  2. 2025MemOS: A Memory OS for AI Systemcited by 138
  3. 2024LongLaMP: A Benchmark for Personalized Long-form Text Generationcited by 97
  4. 2024Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistancecited by 87
  5. 2024Wukong: Towards a Scaling Law for Large-Scale Recommendationcited by 74
  6. 2024PersonalLLM: Tailoring LLMs to Individual Preferencescited by 60
  7. 2025PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistantscited by 48
  8. 2026CL-bench: A Benchmark for Context Learningcited by 47
  9. 2025Training Proactive and Personalized LLM Agentscited by 46
  10. 2025ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptionscited by 45
  11. 2024LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendationscited by 40
  12. 2018Seq2Slate: Re-ranking and Slate Optimization with RNNscited by 39
  13. 2023RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendationcited by 36
  14. 2024Linear-Time Graph Neural Networks for Scalable Recommendationscited by 31
  15. 2025LaMP-QA: A Benchmark for Personalized Long-form Question Answeringcited by 31
  16. 2024Score-based Generative Diffusion Models for Social Recommendationscited by 23
  17. 2023Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Metacited by 21
  18. 2025OpenOneRec Technical Reportcited by 16
  19. 2026PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Recordscited by 16
  20. 2026ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Datacited by 16
  21. 2024LLMs for User Interest Exploration in Large-scale Recommendation Systemscited by 15
  22. 2025PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalizationcited by 15
  23. 2022PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendationcited by 12
  24. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 12
  25. 2026How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistantscited by 9
  26. 2026EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environmentscited by 9
  27. 2026OneReason Technical Reportcited by 8
  28. 2025User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systemscited by 6
  29. 2026π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflowscited by 6
  30. 2025Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answeringcited by 5
  31. 2026Agentic Recommender System with Hierarchical Belief-State Memorycited by 5
  32. 2025Avoiding Over-Personalization with Rule-Guided Knowledge Graph Adaptation for LLM Recommendationscited by 3
  33. 2026GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verificationcited by 3
  34. 2026OpenJarvis: Personal AI, On Personal Devicescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
  2. 2026PersoPilot: An Adaptive AI-Copilot for Transparent Contextualized Persona Classification and Personalized Response Generation
  3. 2026Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data
  4. 2024PersonaGym: Evaluating Persona Agents and LLMs
  5. 2025Dynamic Evaluation Framework for Personalized and Trustworthy Agents: A Multi-Session Approach to Preference Adaptability
  6. 2026From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents
  7. 2025ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation
  8. 2026PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents