Coworking AI agents operating within local file systems are rapidly emerging as a paradigm in human-AI interaction; however, effective personalization remains limited by severe data constraints, as strict privacy barriers and the difficulty of jointly collecting multimodal real-world traces prevent scalable training and evaluation, and existing methods remain interaction-centric while overlooking dense behavioral traces in file-system operations; to address this gap, we propose FileGram, a comprehensive framework that grounds agent memory and personalization in file-system behavioral traces, comprising three core components: (1) FileGramEngine, a scalable persona-driven data engine that simulates realistic workflows and generates fine-grained multimodal action sequences at scale; (2) FileGramBench, a diagnostic benchmark grounded in file-system behavioral traces for evaluating memory systems on profile reconstruction, trace disentanglement, persona drift detection, and multimodal grounding; and (3) FileGramOS, a bottom-up memory architecture that builds user profiles directly from atomic actions and content deltas rather than dialogue summaries, encoding these traces into procedural, semantic, and episodic channels with query-time abstraction; extensive experiments show that FileGramBench remains challenging for state-of-the-art memory systems and that FileGramEngine and FileGramOS are effective, and by open-sourcing the framework, we hope to support future research on personalized memory-centric file-system agents.

翻译：协同工作的AI智能体在本地文件系统中运行，正迅速成为人机交互的新范式。然而，严格的隐私壁垒与多模态真实世界轨迹联合采集的困难，导致可扩展的训练与评估严重受限，使得有效的个性化仍然受到数据约束的制约；同时，现有方法仍以交互为中心，忽视了文件系统操作中密集的行为轨迹。为填补这一空白，我们提出FileGram，一个将智能体记忆与个性化扎根于文件系统行为轨迹的综合框架，包含三个核心组件：(1) FileGramEngine，一个可扩展的、基于角色驱动的数据引擎，能够模拟真实工作流并大规模生成细粒度的多模态动作序列；(2) FileGramBench，一个基于文件系统行为轨迹的诊断基准，用于评估记忆系统在档案重建、轨迹解缠、角色漂移检测以及多模态扎根方面的能力；(3) FileGramOS，一种自底向上的记忆架构，直接从原子动作和内容差异（而非对话摘要）构建用户档案，将这些轨迹编码进程序性、语义性和情境性通道，并提供查询时的抽象机制。大量实验表明，FileGramBench对最先进的记忆系统仍具有挑战性，而FileGramEngine与FileGramOS是有效的。通过开源此框架，我们期望支持未来关于以个性化记忆为中心的文件系统智能体的研究。