EgoMemReason: A Memory-driven Reasoning Benchmark
for Long-Horizon Egocentric Video Understanding

Abstract

Next-generation visual assistants such as smart glasses, embodied agents, and always-on life-logging systems must reason over an entire day or more of continuous visual experience. In such ultra-long video settings, relevant information is sparsely distributed across hours or days, making memory a fundamental challenge: models must accumulate information over time, recall previously observed states, track temporal order, and abstract recurring patterns from past experience. However, existing week-long video benchmarks are still primarily designed for perception and recognition, such as locating a specific moment or summarizing global content, rather than reasoning that requires accumulating and integrating evidence across multiple days. To address this gap, we introduce EgoMemReason, a comprehensive benchmark that systematically evaluates week-long egocentric video understanding through the lens of memory-driven reasoning. EgoMemReason evaluates three complementary memory types: entity memory, tracking how object states evolve and change across days; event memory, recalling and ordering activities separated by hours or days; and behavior memory, abstracting recurring patterns from sparse, repeated observations over the whole week period. EgoMemReason comprises 500 questions across three memory types and six core challenges, with an average of 5.1 video segments of evidence per question and 25.9 hours of memory backtracking. We evaluate EgoMemReason on 17 methods across MLLMs and agentic frameworks, revealing that even the best model achieves only 39.6% overall accuracy. Further analysis shows that the three memory types fail for distinct reasons and that performance degrades as evidence spans longer temporal horizons, revealing that long-horizon memory remains far from solved. We believe EgoMemReason establishes a strong foundation for evaluating and advancing long-context, memory-aware multimodal systems.

Three Memory Types · Six Core Challenges

We decompose week-long memory into three complementary types inspired by cognitive science, each operationalized into two tasks targeting distinct reasoning demands.

Figure 3: Overview of the six core challenges across three memory types in EgoMemReason. Within each example, the week-long timeline shows evidence frames sampled at different timestamps (e.g., D1, D2 denote days, and Q-D5 indicates the query timestamp on Day 5, highlighted by a dashed box). Green frames indicate relevant evidence and red frames indicate distracting observations.

Results

We evaluate 17 systems spanning general-purpose MLLMs, video-specific MLLMs, and agentic video frameworks. The strongest model reaches only 39.6% overall — long-horizon memory is far from solved.
Submit your method to the public leaderboard: huggingface.co/spaces/Ted412/EgoMemReason.

Table 1: Main benchmark results on EgoMemReason. Accuracy (%) across three memory types and six capability dimensions: Tracking (Cumulative State Tracking), Counting (Temporal Counting), Ordering (Event Ordering), Linking (Event Linking), Spatial (Spatial Preference Inference), and Activity (Activity Pattern Inference). The best result in each column is bolded and the second best is underlined.

Citation

@misc{wang2026egomemreasonmemorydrivenreasoningbenchmark,
      title={EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding},
      author={Ziyang Wang and Yue Zhang and Shoubin Yu and Ce Zhang and Zengqi Zhao and Jaehong Yoon and Hyunji Lee and Gedas Bertasius and Mohit Bansal},
      year={2026},
      eprint={2605.09874},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2605.09874},
}