paper-with-me

Papers

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

2025-05-23 · Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo, Jiahao Li, Bin Li, Houqiang Li, Yan Lu

Long-form video understanding presents significant challenges due to extensive temporal-spatial complexity and the difficulty of question answering under such extended contexts. While Large Language Models (LLMs) have demonstrated considerable advancements in video analysis capabilities and long context handling, they continue to exhibit limitations when processing information-dense hour-long videos. To overcome such limitations, we propose the Deep Video Discovery agent to leverage an agentic search strategy over segmented video clips. Different from previous video agents manually designing a rigid workflow, our approach emphasizes the autonomous nature of agents. By providing a set of search-centric tools on multi-granular video database, our DVD agent leverages the advanced reasoning capability of LLM to plan on its current observation state, strategically selects tools, formulates appropriate parameters for actions, and iteratively refines its internal reasoning in light of the gathered information. We perform comprehensive evaluation on multiple long video understanding benchmarks that demonstrates the advantage of the entire system design. Our DVD agent achieves SOTA performance, significantly surpassing prior works by a large margin on the challenging LVBench dataset. Comprehensive ablation studies and in-depth tool analyses are also provided, yielding insights to further advance intelligent agents tailored for long-form video understanding tasks. The code will be released later.

📄 PDF Abstract BibTeX arXiv:2505.18079

Code (0)

등록된 구현이 없습니다.

Tasks

FormQuestion AnsweringVideo Understanding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

VideoDeepResearch: Long Video Understanding With Agentic Tool Using

2025-06-12 · Huaying Yuan, Zheng Liu, Junjie Zhou, Ji-Rong Wen 외

Long video understanding (LVU) presents a significant challenge for current multi-modal large language models (MLLMs) due to the task's inherent complexity and context window constraint. It is widely assumed that address…

MMEVideo MMEVideo Understanding

VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning

2026-01-22 · Chenglin Li, Qianglong Chen, Feng Han, Yikun Wang 외 arxiv

Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames, which weakens temporal localization and …

LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos

2026-03-15 · Rongyi Yu, Chenyuan Duan, Wentao Zhang arxiv

Long video question answering (Long-Video QA) increasingly relies on agentic tool use to retrieve evidence from long videos. In realistic settings, this process often requires multi-hop retrieval, where agents must itera…

Video Question AnsweringAnswer GenerationCausal InferenceVisual Tracking

Rethinking Scientific Discovery in the Agentic Era

2026-07-04 · Yining Zheng, Yuxin Wang, Jiahao Lu, Shicheng Fang 외 arxiv

Artificial intelligence has advanced scientific discovery, but most AI4Science systems remain fragmented tools that rely on humans to coordinate problem formulation, literature grounding, model use, simulation, validatio…

Exploring Modularity of Agentic Systems for Drug Discovery

2025-06-27 · Laura van Weesep, Samuel Genheden, Ola Engkvist, Jens Sjölund

Large-language models (LLMs) and agentic systems present exciting opportunities to accelerate drug discovery and design. In this study, we critically examine the modularity of LLM-based agentic systems for drug discovery…

Drug Discovery