{"slug": "egocite-context-augmented-indexing-and-time-aware-retrieval-for-long-horizon", "title": "EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory", "summary": "Researchers introduced EgoCITE, a long-horizon agentic memory framework for egocentric question answering that improves accuracy by 4.4–14.2% over agentic memory baselines while achieving 36× lower cost than long-context LLM agents. The framework, detailed in arXiv:2608.12627v1, addresses bottlenecks in existing systems by using context-augmented indexing and time-aware retrieval, evaluated on EgoLifeQA, EgoMem, and EgoR1-Bench.", "body_md": "arXiv:2608.12627v1 Announce Type: new\nAbstract: Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in existing systems: indices built from context-poor captions are unreliable for agentic search, while retrieval ignores a question's temporal intent. To address both bottlenecks, we introduce EgoCITE (Egocentric Context-augmented Indexing and Time-aware Evidence retrieval), a long-horizon agentic memory framework for egocentric QA. EgoCITE comprises three components. EgoScheme uses local multimodal context to turn fragmentary video captions and speech transcripts into self-contained atomic memory indices. EgoIndex organizes complementary action, activity, utterance, and conversation representations into searchable multi-view memory indices at multiple granularities. EgoRetrv combines semantic search with question-conditioned temporal relevance scoring and curation of retrieved evidence. We evaluate EgoCITE on EgoLifeQA, EgoMem, and EgoR1-Bench in terms of answer accuracy and target-event retrieval alignment. EgoCITE improves accuracy over agentic memory baselines by at least 4.4--14.2\\% while achieving 36$\\times$ lower cost than long-context LLM agents.", "url": "https://wpnews.pro/news/egocite-context-augmented-indexing-and-time-aware-retrieval-for-long-horizon", "canonical_source": "https://arxiv.org/abs/2608.12627", "published_at": "2026-08-14 04:00:00+00:00", "updated_at": "2026-08-14 04:06:28.901778+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research"], "entities": ["EgoCITE", "EgoLifeQA", "EgoMem", "EgoR1-Bench", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/egocite-context-augmented-indexing-and-time-aware-retrieval-for-long-horizon", "markdown": "https://wpnews.pro/news/egocite-context-augmented-indexing-and-time-aware-retrieval-for-long-horizon.md", "text": "https://wpnews.pro/news/egocite-context-augmented-indexing-and-time-aware-retrieval-for-long-horizon.txt", "jsonld": "https://wpnews.pro/news/egocite-context-augmented-indexing-and-time-aware-retrieval-for-long-horizon.jsonld"}}