HippoCamp: Benchmarking Contextual Agents on Personal Computers

TL;DR

HippoCamp is a new benchmark for evaluating multimodal file management agents in personal, user-centric environments, highlighting current limitations and guiding future AI assistant development.

Contribution

It introduces a comprehensive, real-world dataset and evaluation framework for multimodal agents handling personal files, emphasizing detailed failure analysis.

Findings

State-of-the-art models achieve only 48.3% accuracy in user profiling.

Long-horizon retrieval and cross-modal reasoning are major challenges.

Perception and evidence grounding are key bottlenecks in current systems.

Abstract

We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. Unlike existing agent benchmarks that focus on tasks like web interaction, tool use, or software automation in generic settings, HippoCamp evaluates agents in user-centric environments to model individual user profiles and search massive personal files for context-aware reasoning. Our benchmark instantiates device-scale file systems over real-world profiles spanning diverse modalities, comprising 42.4 GB of data across over 2K real-world files. Building upon the raw files, we construct 581 QA pairs to assess agents' capabilities in search, evidence perception, and multi-step reasoning. To facilitate fine-grained analysis, we provide 46.1K densely annotated structured trajectories for step-wise failure diagnosis. We evaluate a wide range of state-of-the-art multimodal large language models (MLLMs) and agentic methods on HippoCamp. Our comprehensive experiments reveal a significant performance gap: even the most advanced commercial models achieve only 48.3% accuracy in user profiling, struggling particularly with long-horizon retrieval and cross-modal reasoning within dense personal file systems. Furthermore, our step-wise failure diagnosis identifies multimodal perception and evidence grounding as the primary bottlenecks. Ultimately, HippoCamp exposes the critical limitations of current agents in realistic, user-centric environments and provides a robust foundation for developing next-generation personal AI assistants.