Paper Citation Record · LEDGER

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

As of 22 August 2026, this Paper Citation Record lists 85 of 85 outbound references and 11 inbound Pith citation observations for arXiv:2512.05774.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2512.05774 v2

Coverage vector

measured 85 of 85 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T18:22:33.231784Z

measured 96 of 96 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:35:26.623428Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-03T15:28:33.947770Z

Reference resolution

85 of 85 outbound references displayed

verified exact0
verified fuzzy0
unresolved84
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ab07ad85-2248-4752-af36-3559ed0356f4 · outbound

This paper cites Psychology Press,.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Psychology Press,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:23.527845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0979b839-73ae-4a52-8a19-cc714b8676c9 · outbound

This paper cites Temporal chain of thought: Long-video understanding by thinking in frames, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Temporal chain of thought: Long-video understanding by thinking in frames, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:23.597949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f03292c-2032-4565-b079-2752b514e104 · outbound

This paper cites Qwen2.5-VL Technical Report.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:23.657740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d99e710b-87bc-46e2-b2bb-08b3c58d2bcd · outbound

This paper cites Active perception.Proceedings of the IEEE, 76(8):966–1005, 1988.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Active perception.Proceedings of the IEEE, 76(8):966–1005, 1988

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:23.725387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a5e3cfe-1e3b-4420-b5a3-e6927aeb36be · outbound

This paper cites an unresolved cited work.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:23.836886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8550eae5-9bca-4c99-8114-ea05c2beb871 · outbound

This paper cites Revisiting the “Video” in Video-Language Understanding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Revisiting the “Video” in Video-Language Understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:23.954077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5b78b50-cced-4924-b0c2-b7cbc42108e1 · outbound

This paper cites Hadzic, Taran Kota, Jimming He, Cristobal Eyzaguirre, Zane Durante, Manling Li, Jiajun Wu, and Li Fei-Fei.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Hadzic, Taran Kota, Jimming He, Cristobal Eyzaguirre, Zane Durante, Manling Li, Jiajun Wu, and Li Fei-Fei

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:24.071228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6c8446-6848-47c6-9f25-d3ddc059263b · outbound

This paper cites Lvagent: Long video under- standing by multi-round dynamical collaboration of mllm agents.arXiv preprint arXiv:2503.10200, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Lvagent: Long video under- standing by multi-round dynamical collaboration of mllm agents.arXiv preprint arXiv:2503.10200, 2025

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:24.284882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deaf634e-0f3c-48a4-949b-3bffd6c46c17 · outbound

This paper cites Longvila: Scaling long-context visual language models for long videos,.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Longvila: Scaling long-context visual language models for long videos,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:24.500550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab6de7d-87f0-45bd-942a-646db4b28c65 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capabil- ity in llms via reinforcement learning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Deepseek-r1: Incentivizing reasoning capabil- ity in llms via reinforcement learning, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:24.635886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb4b9c68-1c53-4556-b642-dc18befe91d5 · outbound

This paper cites See what you need: Query-aware visual intelligence through reasoning-perception loops, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding See what you need: Query-aware visual intelligence through reasoning-perception loops, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:24.740213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8c5a29f-c674-4f3f-9044-c2efc0b0b7d9 · outbound

This paper cites Agentic keyframe search for video question answering, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Agentic keyframe search for video question answering, 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:24.903019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a9f88bc-a7c9-455e-9640-acddcc9f2a6c · outbound

This paper cites Videoagent: A memory-augmented multi- modal agent for video understanding, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Videoagent: A memory-augmented multi- modal agent for video understanding, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.067335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39d9c632-a053-4ba3-ae37-12a08dfcbd05 · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.203479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f3990bf-f693-454b-9f2b-671870d8e6a7 · outbound

This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.296291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0038f4c-31d6-4a46-993d-fff38859e842 · outbound

This paper cites Love-r1: Advancing long video understanding with an adaptive zoom-in mechanism via multi- step reasoning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Love-r1: Advancing long video understanding with an adaptive zoom-in mechanism via multi- step reasoning, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.458253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 766d3b5e-c281-4990-b36b-46392ae6fc2e · outbound

This paper cites Framemind: Frame-interleaved video reasoning via reinforcement learning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Framemind: Frame-interleaved video reasoning via reinforcement learning, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.562342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f2603e6-7635-4503-9759-a25615faac7a · outbound

This paper cites Framethinker: Learning to think with long videos via multi-turn frame spotlighting, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Framethinker: Learning to think with long videos via multi-turn frame spotlighting, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.668330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 382a94c5-c17e-4d1b-8216-c14d2a5dc0ae · outbound

This paper cites Adaptive video understanding agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Adaptive video understanding agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.818730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 890b45a3-048d-4226-b78d-f82a5079b549 · outbound

This paper cites Language repository for long video understanding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Language repository for long video understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.912949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a609a22e-1532-431d-874e-840a93ff94d5 · outbound

This paper cites Videomultiagents: A multi-agent framework for video question answering, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Videomultiagents: A multi-agent framework for video question answering, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:25.998750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 262ee400-c61d-4a27-bdf0-8b6e971c0587 · outbound

This paper cites Aria: An open multimodal native mixture-of- experts model, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Aria: An open multimodal native mixture-of- experts model, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:26.168260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0443557b-3779-4956-8287-b4338890baad · outbound

This paper cites BLIP: Bootstrapping language-image pre-training for unified vision- language understanding and generation.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding BLIP: Bootstrapping language-image pre-training for unified vision- language understanding and generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:26.390300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5e69584-5200-4fa3-af81-4031da93e4d1 · outbound

This paper cites Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:26.553542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 001a86da-c99c-44df-80e1-33be32c08153 · outbound

This paper cites VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:26.641945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f810102-3f8f-484f-9f81-e56ce2ae8592 · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:26.762749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26962856-9399-4286-ac5d-1ca9184f4e80 · outbound

This paper cites Videomind: A chain-of-lora agent for long video reasoning.arXiv preprint arXiv:2503.13444, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Videomind: A chain-of-lora agent for long video reasoning.arXiv preprint arXiv:2503.13444, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:26.967561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c8a033b-4daa-4509-a97c-29ee15866f44 · outbound

This paper cites Video-rag: Visually-aligned retrieval-augmented long video comprehension, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Video-rag: Visually-aligned retrieval-augmented long video comprehension, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.084218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a637fc8-5cf3-487b-a4c9-cf1a96e1e427 · outbound

This paper cites Video active perception: Efficient inference-time long-form video understanding with vision-language models.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Video active perception: Efficient inference-time long-form video understanding with vision-language models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.138082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cee4a0c-a239-4bad-b23a-d498d99d529c · outbound

This paper cites Drvideo: Document retrieval based long video understanding, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Drvideo: Document retrieval based long video understanding, 2024

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.224491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05599ce7-37fc-452c-abec-68d460b0c9e9 · outbound

This paper cites Caviar: Critic- augmented video agentic reasoning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Caviar: Critic- augmented video agentic reasoning, 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.307201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49631c8e-88ed-4461-a3c3-7fc26d48f1c2 · outbound

This paper cites Morevqa: Exploring modular reasoning models for video question answering, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Morevqa: Exploring modular reasoning models for video question answering, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.377043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f4cec4-ea96-4fd3-9f37-7fdb3c242dbd · outbound

This paper cites Minerva: Evaluating complex video reasoning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Minerva: Evaluating complex video reasoning, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.424656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff1b48f-623d-4978-845b-eb7449aa3c95 · outbound

This paper cites Gpt-4o system card, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Gpt-4o system card, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.486611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 132af810-d857-4e6f-a1eb-be56ab1e266f · outbound

This paper cites Gpt-5 system card.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Gpt-5 system card

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.558715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99181d7a-f852-4af0-8980-2471e20ddb0a · outbound

This paper cites Introducing gpt-4.1 in the api.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Introducing gpt-4.1 in the api

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.648141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911c8666-d36a-4a65-b883-971d8ce3b972 · outbound

This paper cites Openai o3 and o4-mini system card.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Openai o3 and o4-mini system card

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.738975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd44134-331c-4ae9-af8e-7cf9453fe103 · outbound

This paper cites Conan: Progressive learning to reason like a detective over multi-scale visual evidence, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Conan: Progressive learning to reason like a detective over multi-scale visual evidence, 2025

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:27.892470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e77f76e3-50af-4a2a-8762-2e1d9b573389 · outbound

This paper cites mapreduce.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding mapreduce

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.061767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af23dfd3-3c97-4ace-a30a-6c7158542e7e · outbound

This paper cites an unresolved cited work.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.145393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 619ddfdf-c83b-45bd-a8c6-fc89ff2b5cdf · outbound

This paper cites Understanding long videos in one multimodal language model pass.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Understanding long videos in one multimodal language model pass

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.284376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12dd4acb-da3c-436d-b321-44e1a56ecbb5 · outbound

This paper cites Ryoo, Honglu Zhou, Shrikant Kendre, Can Qin, Le Xue, Manli Shu, Jongwoo Park, Kanchana Ranasinghe, Silvio Savarese, Ran Xu, Caiming Xiong, and Juan Carlos Niebles.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Ryoo, Honglu Zhou, Shrikant Kendre, Can Qin, Le Xue, Manli Shu, Jongwoo Park, Kanchana Ranasinghe, Silvio Savarese, Ran Xu, Caiming Xiong, and Juan Carlos Niebles

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.409448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 087a47bf-97b4-4a42-aae8-c0b9f794f8db · outbound

This paper cites an unresolved cited work.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.572270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e21123ba-21f9-4d4f-a740-e8356176de58 · outbound

This paper cites LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.724700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 490429ce-0cf9-43c4-be67-7f09c0650180 · outbound

This paper cites Vgent: Graph-based retrieval-reasoning-augmented generation for long video understanding, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Vgent: Graph-based retrieval-reasoning-augmented generation for long video understanding, 2025

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.882214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ddc866-bff3-4019-abdb-451f732f8fd9 · outbound

This paper cites Enhanc- ing video-llm reasoning via agent-of-thoughts distillation,.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Enhanc- ing video-llm reasoning via agent-of-thoughts distillation,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:28.991847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0b2081b-5f53-4d21-8b42-08d2cc83303b · outbound

This paper cites Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:29.150095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e234f49-5701-4ddd-9fb5-01a86e983313 · outbound

This paper cites Scene exploration by vision-language models,.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Scene exploration by vision-language models,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:29.221334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa5167e0-e596-42fc-a9fd-4e1682a1dbce · outbound

This paper cites Adaptive keyframe sampling for long video understanding, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Adaptive keyframe sampling for long video understanding, 2025

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:29.372562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d5d6bbf-c1e9-4f25-9bfb-b5f651670046 · outbound

This paper cites Moss-chatv: Reinforcement learning with process reasoning reward for video temporal reasoning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Moss-chatv: Reinforcement learning with process reasoning reward for video temporal reasoning, 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:29.477922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87eb7486-4da8-47a0-b224-99d022bbcb82 · outbound

This paper cites Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities, 2025

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:29.633102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18b20e16-d5a0-4109-86bd-9bc1c76dc5e9 · outbound

This paper cites Qwen3-vl: A general vision-language model.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Qwen3-vl: A general vision-language model

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:29.838794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e776a9fe-6365-4d5a-9a4f-f9700f38a5e4 · outbound

This paper cites Seed1.5-vl technical report, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Seed1.5-vl technical report, 2025

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:30.027703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cae0a9-08a6-4b36-b17d-45cc3b815ccb · outbound

This paper cites Tarsier: Recipes for training and evaluating large video description models, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Tarsier: Recipes for training and evaluating large video description models, 2024

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:30.241779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f36d90b2-6847-4ac8-beb3-1267664dc549 · outbound

This paper cites Videorft: Incentivizing video reasoning capability in mllms via reinforced fine-tuning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Videorft: Incentivizing video reasoning capability in mllms via reinforced fine-tuning, 2025

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:30.363995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1f8c0b5-cc6a-4f5d-af24-f97a3fe5713f · outbound

This paper cites Vamos: Versatile action models for video understanding, 2023.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Vamos: Versatile action models for video understanding, 2023

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:30.550128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6265b3ef-4462-417f-9743-97636983d1a9 · outbound

This paper cites Alvarez, Lei Zhang, and Zhiding Yu.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Alvarez, Lei Zhang, and Zhiding Yu

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:30.715885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff1aabae-64f4-4165-a500-5d40bcea4c2f · outbound

This paper cites thinking with videos.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding thinking with videos

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:30.823378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71804053-5966-4169-a2a3-7532df86e9e2 · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:30.883136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b39fdc55-995d-479d-8887-7be32c9ce189 · outbound

This paper cites Videoagent: Long-form video understanding with large language model as agent, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Videoagent: Long-form video understanding with large language model as agent, 2024

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.006785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf36da34-5af5-4ead-bb12-041df948da16 · outbound

This paper cites Adaretake: Adaptive redundancy reduction to perceive longer for video-language understanding, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Adaretake: Adaptive redundancy reduction to perceive longer for video-language understanding, 2025

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.129405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 092753b1-aab3-4aee-806c-3130dd836dc9 · outbound

This paper cites Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.236016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecc2491c-45b2-4cab-bf74-e1e0057f03fa · outbound

This paper cites VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.365284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b369d48e-fe31-46df-bd24-a9df4d21cbb2 · outbound

This paper cites Videochat-a1: Thinking with long videos by chain-of-shot reasoning, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Videochat-a1: Thinking with long videos by chain-of-shot reasoning, 2025

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.498639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b3596d-ed6b-4f1a-9adb-0972a57588e4 · outbound

This paper cites Video-RTS: Re- thinking reinforcement learning and test-time scaling for ef- ficient and enhanced video reasoning.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Video-RTS: Re- thinking reinforcement learning and test-time scaling for ef- ficient and enhanced video reasoning

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.638487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fce5a10f-891c-46f8-8bad-75a845ac952b · outbound

This paper cites Longvideobench: A benchmark for long-context interleaved video-language understanding.Advances in Neural Informa- tion Processing Systems, 37:28828–28857, 2024.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Longvideobench: A benchmark for long-context interleaved video-language understanding.Advances in Neural Informa- tion Processing Systems, 37:28828–28857, 2024

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.768007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 149c61bb-fc16-4a96-9749-ad062f8d1013 · outbound

This paper cites Vision in action: Learning active perception from human demonstrations, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Vision in action: Learning active perception from human demonstrations, 2025

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.863417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8f813f9-4627-43ba-a7b0-2668afa96c4c · outbound

This paper cites LVBench: An Extreme Long Video Understanding Benchmark.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding LVBench: An Extreme Long Video Understanding Benchmark

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:31.984503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86733491-3b8a-4b3c-809b-1c36a5df3da9 · outbound

This paper cites Ava: To- wards agentic video analytics with vision language models,.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Ava: To- wards agentic video analytics with vision language models,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.088897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c3b0acc-dca0-43c3-8a5e-8d78aea8b37e · outbound

This paper cites Generative Frame Sampler for Long Video Understanding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Generative Frame Sampler for Long Video Understanding

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.132710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38331be7-93c8-4c26-bff3-c5e9b0faef54 · outbound

This paper cites Re-thinking temporal search for long- form video understanding, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Re-thinking temporal search for long- form video understanding, 2025

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.183016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8569c7d-3f0f-4825-8be2-47c14e8f7893 · outbound

This paper cites End-to-end learning of action detection from frame glimpses in videos.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding End-to-end learning of action detection from frame glimpses in videos

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.259304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aac6a72-52bf-480a-951c-0ed00dfe12b4 · outbound

This paper cites Self-chained image-language model for video localization and question answering.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Self-chained image-language model for video localization and question answering

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.320679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0414c75e-1cd8-4249-b2e6-2879148ed658 · outbound

This paper cites Videoex- plorer: Think with videos for agentic long-video understand- ing, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Videoex- plorer: Think with videos for agentic long-video understand- ing, 2025

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.363429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a4a2750-876e-4854-b316-4c81608b8cc8 · outbound

This paper cites A simple llm framework for long-range video question-answering, 2023.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding A simple llm framework for long-range video question-answering, 2023

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.419785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 980d2234-069b-411b-86f1-5cef7ff19c02 · outbound

This paper cites Silvr: A simple language-based video rea- soning framework, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Silvr: A simple language-based video rea- soning framework, 2025

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.473110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab704eb6-7243-428e-b602-cab8b96c728c · outbound

This paper cites Thinking with videos: Multimodal tool- augmented reinforcement learning for long video reasoning,.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Thinking with videos: Multimodal tool- augmented reinforcement learning for long video reasoning,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.545083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82e609f1-d849-4451-89ca-dde64e8fbb9e · outbound

This paper cites Long Context Transfer from Language to Vision.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Long Context Transfer from Language to Vision

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.646227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 769280f2-ed68-4882-8a21-12a21bf414ea · outbound

This paper cites Deep video discovery: Agentic search with tool use for long-form video understanding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Deep video discovery: Agentic search with tool use for long-form video understanding

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.730480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67934772-bf1f-4c7c-b7cf-dd600c3842b5 · outbound

This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.845533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f027c173-a06d-429c-a644-f5f35ad74c61 · outbound

This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding MLVU: Benchmarking Multi-task Long Video Understanding

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.900214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 200105ba-b457-4315-ac7d-5d04921ef0d5 · outbound

This paper cites Reagent-v: A reward-driven multi-agent framework for video understand- ing, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Reagent-v: A reward-driven multi-agent framework for video understand- ing, 2025

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:32.953045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c19dd3-b2f3-42dc-a70c-1abfcae64bf0 · outbound

This paper cites Active-o3: Empowering multimodal large language models with active perception via grpo, 2025.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding Active-o3: Empowering multimodal large language models with active perception via grpo, 2025

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:33.016012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8804358-9b18-4108-8265-4f6569830d65 · outbound

This paper cites A.i.r.: Enabling adaptive, iterative, and reasoning-based frame selection for video question answering,.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding A.i.r.: Enabling adaptive, iterative, and reasoning-based frame selection for video question answering,

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-03T18:22:33.147794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17bc61a3-56c6-4fe4-ad3b-890354a3163c · outbound

This paper cites usually range from 4 to 5 feet in length.

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding usually range from 4 to 5 feet in length

Reference 85

Resolution: malformed identifier; no resolver link, observed 2026-08-03T18:22:33.231784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1912ee73-8485-4f2d-9144-2047a4d59586 · inbound

EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding cites this paper.

EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 72

Resolution: metadata mismatch; arxiv_id, observed 2026-06-05T02:15:31.456438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 86164427-32ac-4232-b257-fb932e53e883 · inbound

Personal Visual Context Learning in Large Multimodal Models cites this paper.

Personal Visual Context Learning in Large Multimodal Models Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-06-05T02:15:31.456438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 734bca2d-c3c2-43d1-bad0-151018abff92 · inbound

Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval cites this paper.

Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-05T02:15:31.456438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f96c7881-8649-401f-973e-f129e244a4c6 · inbound

Benchmarking Visual State Tracking in Multimodal Video Understanding cites this paper.

Benchmarking Visual State Tracking in Multimodal Video Understanding Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:46:28.019866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b81f57c6-b73c-4239-8309-38574c2ad9a9 · inbound

Watch, Remember, Reason: Human-View Video Understanding with MLLMs cites this paper.

Watch, Remember, Reason: Human-View Video Understanding with MLLMs Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 230

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T17:27:15.077171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dfab930b-09ce-410f-b217-5ca8bc44e275 · inbound

Rethinking RAG in Long Videos: What to Retrieve and How to Use It? cites this paper.

Rethinking RAG in Long Videos: What to Retrieve and How to Use It? Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 66

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T15:28:33.949814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b2160f28-107f-4777-aa54-4fcf8fa980b3 · inbound

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA cites this paper.

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T21:09:45.205921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a95a9a-82d5-4324-8595-74302ef3e2b5 · inbound

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding cites this paper.

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T02:59:25.213497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dbe0cc8-4ad6-44f9-a539-8402412a25ad · inbound

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding cites this paper.

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T01:46:07.582823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73d96fa0-a39a-4bc8-b68c-deef7daed697 · inbound

SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning cites this paper.

SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T00:43:38.391136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4451c8-e1d5-4fe0-8868-2e4a348865b4 · inbound

REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering cites this paper.

REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T04:35:26.623428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.