aiqbench analysis
GROVE introduces a training-free framework enabling wearable AI assistants to causally grow memory from continuous video streams, supporting both reactive queries and proactive situation awareness. By consolidating perceptual evidence into temporal strata ranging from moments to cross-day patterns, the system outperforms existing methods on lifelong visual benchmarks without requiring retraining. This advancement addresses critical gaps in long-term context retention for embodied AI agents operating over extended periods.
GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience
arXiv:2608.02392v1 Announce Type: cross Abstract: A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream. GROVE retains fine-grained perceptual evidence and incrementally consolidates it into time-stamped moments, coherent episodes, and recurring cross-day patterns. Each stratum is paired with a scale-native retrieval skill for locating an observation, replaying an activity, or traversing long-range regularities. Reactive QA and proactive assistance share this memory and access interface, differing in whether retrieval is initiated by a user query or the current situation. Across multiple benchmarks including the challenging MM-lifelong and EgoServe, GROVE achieves the best results among the compared methods. Controlled ablations show that the temporal strata and their access skills are complementary, with patterns providing the largest benefit when evidence spans multiple days. Code will be available at https://github.com/SitongGong/GROVE.
Abstract:A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream. GROVE retains fine-grained perceptual evidence and incrementally consolidates it into time-stamped moments, coherent episodes, and recurring cross-day patterns. Each stratum is paired with a scale-native retrieval skill for locating an observation, replaying an activity, or traversing long-range regularities. Reactive QA and proactive assistance share this memory and access interface, differing in whether retrieval is initiated by a user query or the current situation. Across multiple benchmarks including the challenging MM-lifelong and EgoServe, GROVE achieves the best results among the compared methods. Controlled ablations show that the temporal strata and their access skills are complementary, with patterns providing the largest benefit when evidence spans multiple days. Code will be available at this https URL.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2608.02392 [cs.CV]
(or arXiv:2608.02392v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.02392 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 272 words
Related coverage
Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents
arXiv · Oct 8, 2026
A Princeton Researcher Proposes Recurrent Looped Transformer (RLT) that Carries Decoder State across Every Token, Fixing 96 Blocks per Token with Unbounded Temporal Depth
MarkTechPost · Sep 13, 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · Jun 12, 2026
EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory
arXiv · Sep 24, 2026