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

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

23 May 2025arXiv:2505.18079archive 2025-07-28

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.

PaperPDFCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2505.18079")

Code

Syntology Ran 0 of 10 code samples harvested from 1 repository linked to this paper; 10 have no recorded run.

By repository: found in paper text by Syntology: 10 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/DeepVideoDiscovery found in paper text by SyntologyMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 0 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

10unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from microsoft/DeepVideoDiscovery. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

as_json_schema microsoft/DeepVideoDiscovery/dvd/func_call_shema.py found in paper text by Syntology unverified MIT (permissive) · 27bf334776feb4be · report
assemble_zip microsoft/DeepVideoDiscovery/reproduce/decode_frames.py found in paper text by Syntology unverified MIT (permissive) · c907ab3626ac15fd · report
convert_seconds_to_hhmmss microsoft/DeepVideoDiscovery/dvd/frame_caption.py found in paper text by Syntology unverified MIT (permissive) · aca54d439555eaaf · report
doc microsoft/DeepVideoDiscovery/dvd/func_call_shema.py found in paper text by Syntology unverified MIT (permissive) · c7115c8278660151 · report
find_all_parts microsoft/DeepVideoDiscovery/reproduce/decode_frames.py found in paper text by Syntology unverified MIT (permissive) · 3dddbd13049fdd13 · report
gather_frames_from_time_ranges microsoft/DeepVideoDiscovery/dvd/frame_caption.py found in paper text by Syntology unverified MIT (permissive) · 20cc266a8bd12f47 · report
get_parameters_schema microsoft/DeepVideoDiscovery/dvd/func_call_shema.py found in paper text by Syntology unverified MIT (permissive) · 87a1b0abc5debf84 · report
get_video_id microsoft/DeepVideoDiscovery/mcp_server.py found in paper text by Syntology unverified MIT (permissive) · 2d2eb7325321580c · report
local_image_to_data_url microsoft/DeepVideoDiscovery/dvd/utils.py found in paper text by Syntology unverified MIT (permissive) · 31bb18c44ed2df47 · report
retry_with_exponential_backoff microsoft/DeepVideoDiscovery/dvd/utils.py found in paper text by Syntology unverified MIT (permissive) · d7378512b752bfef · report

Tasks

FormQuestion AnsweringVideo Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections