Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning

• URL: http://arxiv.org/abs/2607.02588v1
• Date: Wed, 01 Jul 2026 05:53:09 GMT
• Title: Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning
• Abstract summary: textscHomer is a Hierarchical Online Memory Exploration and Reasoning framework.<n>textscHomer's memory mirrors the multi-scale structure of long videos, ranging from raw perception, to recurring entities, to events connected by explicit temporal and causal relations.<n>textscHomer outperforms the previous best agent method by $+5.5$, $+10.8$, and $+4.4$ points on M3-Bench-robot, M3-Bench-web, and Video-MME-Long.
• Score: 77.7531245219403
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal large language models excel on short clips but struggle on hour-long videos in an online setting, where frames are processed incrementally under limited memory. Existing online methods either retain compact visual representations that lack semantic structure, or build higher-level memory stores organized around temporal proximity rather than explicit causal links, leaving multi-hop narrative reasoning to be reconstructed by the LLM at every query. We bridge this gap with \textsc{Homer}, a Hierarchical Online Memory Exploration and Reasoning framework. \textsc{Homer}'s memory mirrors the multi-scale structure of long videos, ranging from raw perception, to recurring entities, to events connected by explicit temporal and causal relations. Its agentic reasoner then explores this memory the way humans do, locating the relevant scene, looking up details, and composing the answer through multi-round memory retrieval, with a harness that verifies and corrects each step. \textsc{Homer} outperforms the previous best agent method by $+5.5$, $+10.8$, and $+4.4$ points on M3-Bench-robot, M3-Bench-web, and Video-MME-Long, and consistently lifts three various LLM backbones, indicating a model-agnostic structural capability for grounded retrieval over long videos.

Related papers

• Dual-Latent Memory Routing for Vision-Language Reasoning [39.90357280328134]
  Multimodal large language models (MLLMs) have recently made strong progress in vision-language reasoning, yet their performance often degrades as generations grow longer.<n>Inspired by how humans separately recall what they see and what they infer when solving complex tasks, we propose DLMR.<n>It equips MLLMs with Dual Latent Memories: a visual memory that compresses image evidence and a reasoning memory that tracks intermediate conclusions and constraints.
  arXiv  Detail & Related papers  (2026-09-02T10:45:25Z)
• Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding [41.45143308235023]
  We propose MERIT, a simple yet effective framework for ultra-long video understanding.<n>We formulate an episodic multi-key representation that enables precise retrieval of fine-grained memories.<n>MeRIT achieves state-of-the-art performance across three long-video benchmarks.
  arXiv  Detail & Related papers  (2026-08-07T18:00:02Z)
• Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding [47.48582887762574]
  ReMem is a temporal granularity-adaptive selection framework for training-free LongVideoQA.<n>By explicitly preserving temporal information with memory mechanisms, ReMem suppresses redundancy and empowers MLLMs to perform robust multi-granular video reasoning.
  arXiv  Detail & Related papers  (2026-06-30T10:55:56Z)
• MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models [50.25006399944962]
  Memory is essential for large vision-language models to handle long, multimodal interactions.<n>MEMLENS is a benchmark for memory in multimodal multi-session conversations.<n>We evaluate 27 LVLMs and 7 memory-augmented agents.
  arXiv  Detail & Related papers  (2026-05-14T14:41:17Z)
• VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG [33.938909878793815]
  VideoStir is a structured and multimodal intent-aware long-video RAG framework.<n>It structures a video as atemporal graph at clip level, and then performs multi-hop retrieval to aggregate evidence.<n>It also introduces an MLLM-backed intent-relevance scorer that retrieves frames based on their alignment with the query's reasoning intent.
  arXiv  Detail & Related papers  (2026-04-07T04:26:59Z)
• TeleMem: Building Long-Term and Multimodal Memory for Agentic AI [43.36544433800511]
  Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories.<n>We propose TeleMem, a unified long-term and multimodal memory system that maintains coherent user profiles through narrative dynamic extraction.<n>TeleMem surpasses the state-of-the-art Mem0 baseline with 19% higher accuracy, 43% fewer tokens, and a 2.1x speedup on the ZH-4O long-term role-play gaming benchmark.
  arXiv  Detail & Related papers  (2025-12-12T11:24:52Z)
• WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning [66.24870234484668]
  We introduce WorldMM, a novel multimodal memory agent that constructs and retrieves from multiple complementary memories.<n>WorldMM significantly outperforms existing baselines across five long video question-answering benchmarks.
  arXiv  Detail & Related papers  (2025-12-02T05:14:52Z)
• GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory [59.869552603264076]
  We introduce GCAgent, a novel Global-Context-Aware Agent framework that achieves comprehensive long-video understanding.<n>Our core innovation is the Schematic and Narrative Episodic Memory, which structurally models events and their causal and temporal relations into a concise, organized context.<n>Experiments confirm that GCAgent significantly enhances long-video understanding, achieving up to 23.5% accuracy improvement on the Video-MME Long split over a strong MLLM baseline.
  arXiv  Detail & Related papers  (2025-11-15T04:29:00Z)
• VideoLucy: Deep Memory Backtracking for Long Video Understanding [102.37736560263649]
  We propose VideoLucy, a deep memory backtracking framework for long video understanding.<n>Inspired by the human recollection process from coarse to fine, VideoLucy employs a hierarchical memory structure with progressive granularity.<n>VideoLucy significantly outperforms state-of-the-art methods on multiple long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-14T11:59:19Z)
• Episodic Memory Representation for Long-form Video Understanding [52.33907540905242]
  Large Video Language Models excel at general video understanding but struggle with long-form context window limits.<n>We introduce Video-EM, a training free framework inspired by the principles of human memory.<n>Video-EM achieves performance gains of 4-9 percent over respective baselines while utilizing fewer frames.
  arXiv  Detail & Related papers  (2025-08-13T04:33:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.