PersonaMem-v3：面向全平台个人智能以实现全面的用户理解、推荐及智能体任务

中文摘要 AI 辅助

个人智能正成为面向用户的AI智能体的核心前沿领域。为在日常生活中发挥作用，智能体必须在用户偏好、意图、习惯、社会关系及需求随时间展现的各类数字场景中理解用户。当前系统可在单个应用或任务内实现个性化，但整体个人智能的衡量仍不足：智能体如何构建跨场景用户理解、支持可控的推荐系统、跨平台主动行动，以及避免过度个性化。我们提出PersonaMem-v3，这是一个基于真实场景的全平台个人智能基准与评估工具。PersonaMem-v3源自超过100万条匿名化的真实用户交互历史，其中大部分为隐式信号，并用这些信号构建了涵盖社交媒体、聊天机器人、日历及AI伴侣的时间索引式用户数字世界，包含随时间演变的偏好。该基准将个性化、大语言模型（LLM）驱动的推荐、主动性、智能体工具使用及地理时间推理整合到一个框架中，锚定心理学、社会语言学及用户行为理论。它评估AI智能体是否能从跨平台证据中推断全面的用户理解、个性化响应、对社交媒体推荐进行重排序、通过自然语言遵循用户指令，以及在个性化不合适、重复、过时或不必要时弃权（不执行）。PersonaMem-v3指明了LLM驱动的个人智能体的发展方向，这类智能体可与现有可扩展的推荐基础设施协同工作，同时让个性化更具交互性、智能体化，并与真实用户的数字生活体验保持一致。

英文摘要

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follow user steering through natural language, and hold back when personalization would be inappropriate, repetitive, outdated, or unnecessary.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.

发表机构

• Meta
• University of Pennsylvania（宾夕法尼亚大学）
• MIT（麻省理工学院）

机构由 AI 辅助整理，请以论文原文为准。