Problem
Research questions and friction points this paper is trying to address.
Long-term Memory
Mobile Agents
Benchmark
Experiential Intelligence
Personal Learning
MobileMem: Learning from a Year of Mobile Experiences
🤖 AI Summary
This study addresses the scarcity of authentic multimodal experiential data in existing mobile long-term memory benchmarks by constructing the first annual-scale mobile experience memory benchmark and framework. Leveraging a knowledge-driven synthesis pipeline, it generates temporally consistent multimodal trajectories that facilitate multi-hop reasoning and preference inference. This work bridges the critical gap in real-world scenario data and validates agent capabilities in historical recall, present comprehension, and future adaptation. Ultimately, it advances mobile agents beyond mere information retrieval toward a new paradigm of continuous learning-based experiential intelligence.
📝 Abstract
The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous, multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs a knowledge-grounded synthesis pipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text and multimodal settings covering multi-hop and temporal reasoning, knowledge updating, and implicit preference inference. Specifically, MobileMem enables agents to remember the past, understand the present, and adapt to the future. By modeling experiences rather than isolated facts, MobileMem moves memory beyond information retrieval toward experiential intelligence for continuous personal learning.
Innovation
Methods, ideas, or system contributions that make the work stand out.
On-device Long-term Memory
Experiential Intelligence
Knowledge-grounded Synthesis
Mobile Benchmark
Continuous Personal Learning
🔎 Similar Papers
No similar papers found.
