VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning | Paper Citation Record

Observation c6fcef02-2efa-4065-b867-a466e360b740 · outbound

This paper cites Vidi: Large Multimodal Models for Video Understanding and Editing.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Vidi: Large Multimodal Models for Video Understanding and Editing

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d0c8029-e933-4365-bf3b-bbde95798b3c · outbound

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

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Video-mme: The first-ever compre- hensive evaluation benchmark of multi-modal llms in video analysis

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9770625-938f-4bf0-9e65-82515351de30 · outbound

This paper cites Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models.Computational Visual Media, 2025.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models.Computational Visual Media, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7719bab-58cf-4ca3-a6e3-60310c8ea320 · outbound

This paper cites Qwen3-VL Technical Report.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Qwen3-VL Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 443f78e3-d92f-4495-b3c0-5d7ff89028f3 · outbound

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

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 683ccd4f-4c63-4a4a-ac9b-5b1c2838605e · outbound

This paper cites Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4ec630d-a5ea-4bd1-af27-aaf662ae793b · outbound

This paper cites Video-r1: Reinforcing video reasoning in mllms.Advances in Neural Information Processing Systems, 38:99114–99137, 2026.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Video-r1: Reinforcing video reasoning in mllms.Advances in Neural Information Processing Systems, 38:99114–99137, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5ba25b0-06a3-46e5-bb2e-a54b721a84f9 · outbound

This paper cites Scaling rl to long videos.Advances in Neural Information Processing Systems, 38:172842–172870, 2026.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Scaling rl to long videos.Advances in Neural Information Processing Systems, 38:172842–172870, 2026

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ddb54d4-f7cf-40e2-9374-7fffb42bc084 · outbound

This paper cites Video understanding with large language models: A survey.IEEE T ransactions on Circuits and Systems for Video T echnology, 2025.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Video understanding with large language models: A survey.IEEE T ransactions on Circuits and Systems for Video T echnology, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f77ad9-51a3-4339-b527-04f4aaea37a9 · outbound

This paper cites Frame- thinker: Learning to think with long videos via multi-turn frame spotlighting.arXiv preprint arXiv:2509.24304, 2025.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Frame- thinker: Learning to think with long videos via multi-turn frame spotlighting.arXiv preprint arXiv:2509.24304, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76827ce1-ff53-47e5-bcc8-1c7bf879aab3 · outbound

This paper cites LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3258615a-4027-45e1-b313-178e3e05a6de · outbound

This paper cites Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 798e6883-2ae1-4e04-abc0-904269ad5cd9 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d1a72c9-d926-47c6-a6b9-7bdb3a0af390 · outbound

This paper cites Deepmmsearch-r1: Empowering multimodal llms in multimodal web search.arXiv preprint arXiv:2510.12801, 2025.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Deepmmsearch-r1: Empowering multimodal llms in multimodal web search.arXiv preprint arXiv:2510.12801, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4cc0a9d-b670-4d27-84de-5c0d51b51497 · outbound

This paper cites Search-o1: Agentic search-enhanced large reasoning models.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Search-o1: Agentic search-enhanced large reasoning models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6cf177-c0c2-41f9-8207-04c11ed9b167 · outbound

This paper cites MMSearch-R1: Incentivizing LMMs to Search.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning MMSearch-R1: Incentivizing LMMs to Search

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feffd6cd-80b5-4d5a-97b8-c42192368eba · outbound

This paper cites DeepEyesV2: Toward Agentic Multimodal Model.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning DeepEyesV2: Toward Agentic Multimodal Model

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d9f7b2a-258d-4f95-abce-95b558ef355b · outbound

This paper cites Group Sequence Policy Optimization.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Group Sequence Policy Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd19048-251e-4ff4-9a16-d7914b825e6e · outbound

This paper cites Tpru: Advancing temporal and procedural understanding in large multimodal models.arXiv preprint arXiv:2602.18884, 2026.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Tpru: Advancing temporal and procedural understanding in large multimodal models.arXiv preprint arXiv:2602.18884, 2026

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 656fcef4-25f5-4f4f-8375-2596d537be24 · outbound

This paper cites Videorft: Incentivizing video rea- soning capability in mllms via reinforced fine-tuning.Advances in neural information processing systems, 38:4350–4376, 2026.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Videorft: Incentivizing video rea- soning capability in mllms via reinforced fine-tuning.Advances in neural information processing systems, 38:4350–4376, 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f6b69ab-0764-4f39-8248-2fb8e29e7950 · outbound

This paper cites OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf7bec7-5459-495d-869c-3fd177d991bb · outbound

This paper cites WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 751df1ac-b724-469a-82e8-050c6c678ca1 · outbound

This paper cites V-thinker: Interactive thinking with images.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning V-thinker: Interactive thinking with images

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b7d0f5a-21ae-4fc6-b517-b281081e92a0 · outbound

This paper cites Redsearcher: A scalable and cost-efficient framework for long-horizon search agents.arXiv preprint arXiv:2602.14234, 2026.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Redsearcher: A scalable and cost-efficient framework for long-horizon search agents.arXiv preprint arXiv:2602.14234, 2026

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbeb512f-0e81-49e9-9b87-f5db727c0502 · outbound

This paper cites DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71a13db9-846e-474f-8d6c-11d7d650ac45 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Qwen3.5: Towards native multimodal agents, February 2026

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cef116d4-cab9-46ab-b566-e822b49ab5b2 · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Kimi K2.5: Visual Agentic Intelligence

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb26b614-7e17-479d-b9c3-76c849c474ea · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Llamafactory: Unified efficient fine-tuning of 100+ language models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0435e08e-0ffc-4beb-a7b0-52cccf9f911e · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Hybridflow: A flexible and efficient rlhf framework

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd40ba4-af3c-41f1-944e-21f8881b3287 · outbound

This paper cites MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768ad0bd-4cf5-42a4-b61d-2308ef881da9 · outbound

This paper cites Sensenova-mars: Empowering multimodal agentic reasoning and search via reinforcement learning.arXiv preprint arXiv:2512.24330, 2025.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Sensenova-mars: Empowering multimodal agentic reasoning and search via reinforcement learning.arXiv preprint arXiv:2512.24330, 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5589c94-f269-4b71-8af1-98147327e637 · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ecbee64-6f23-42a2-b142-8f75b8e8fb07 · outbound

This paper cites Simplevqa: Multimodal factuality evaluation for multimodal large language models.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Simplevqa: Multimodal factuality evaluation for multimodal large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 694f88f8-ca15-4828-a5aa-3be2e17a4ad2 · outbound

This paper cites Seeking and Updating with Live Visual Knowledge.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Seeking and Updating with Live Visual Knowledge

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523e98f8-707a-411a-9452-4b40d9b9ec04 · outbound

This paper cites Mmvu: Measuring expert-level multi-discipline video understanding.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Mmvu: Measuring expert-level multi-discipline video understanding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d87f45-d161-4e2b-89d4-86125711e09f · outbound

This paper cites Tempcompass: Do video llms really understand videos? InFindings of the Association for Computational Linguistics: ACL 2024, pages 8731–8772, 2024.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Tempcompass: Do video llms really understand videos? InFindings of the Association for Computational Linguistics: ACL 2024, pages 8731–8772, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 403c2c3f-1b87-4da6-a15a-2e3900ab221a · outbound

This paper cites Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7b2a5e-154a-4b36-8dff-eaa170258ae6 · outbound

This paper cites VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9fe5c4-0bab-4d8f-99b8-4419c7795fe0 · outbound

This paper cites GPT-4o System Card.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning GPT-4o System Card

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 490fef11-a3f1-4766-9f34-5b16bfb2da38 · outbound

This paper cites OpenAI GPT-5 System Card.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning OpenAI GPT-5 System Card

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c41b630-854d-4d61-afaa-1a40505c0f31 · outbound

This paper cites A new era of intelligence with gemini 3.Google.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning A new era of intelligence with gemini 3.Google

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afbded39-895e-46c9-8f81-5f7440af272f · outbound

This paper cites Gemini 3 pro model card, May 2026.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Gemini 3 pro model card, May 2026

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 166bf989-92ab-4b3b-9e0a-fe4e7eaaa9bf · outbound

This paper cites Qwen2.5-VL Technical Report.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Qwen2.5-VL Technical Report

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73392426-f97a-43ea-962c-b5d9e7e16716 · outbound

This paper cites Visual Agentic Reinforcement Fine-Tuning.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Visual Agentic Reinforcement Fine-Tuning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86f1ca56-6770-4836-9be8-f7809f7af514 · outbound

This paper cites Videochat-r1.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Videochat-r1

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2b7315-57b6-4530-8d8d-471496b48d4b · outbound

This paper cites MOONSHOT.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning MOONSHOT

Reference 46

Resolution: malformed identifier; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6fbcfc6-fb70-4e43-8841-2df49964f230 · outbound

This paper cites Otherwise, call choose_framesto narrow down the relevant interval.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Otherwise, call choose_framesto narrow down the relevant interval

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d4cfd80-3921-4dbc-8f27-cfb00f688a74 · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b464df-d6ec-411b-b376-be53dedb8798 · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c0ff86-2255-4586-ae6f-e90b046da469 · outbound

This paper cites After any choose_frames call, the assistant must callfind_frameagain before using detail/search tools or producing the final answer.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning After any choose_frames call, the assistant must callfind_frameagain before using detail/search tools or producing the final answer

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3606cd97-a434-40df-a345-fd42808ab1d5 · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc278b3e-f82b-4b68-9881-c4430af7a386 · outbound

This paper cites name": "<function-name>.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning name": "<function-name>

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac5b6bd-24df-411f-9237-bd7d6e4dee7d · outbound

This paper cites Otherwise, it should callchoose_framesto narrow down the search interval.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Otherwise, it should callchoose_framesto narrow down the search interval

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae105fe4-4865-43a3-bb46-7ceca1b12e45 · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4cdf20c-e068-490a-863f-14bcea71872f · outbound

This paper cites After locking a frame, the assistant may call zoom_in to inspect details, then decide whether to use image_search or web_search.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning After locking a frame, the assistant may call zoom_in to inspect details, then decide whether to use image_search or web_search

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9093353-cf64-424b-8e81-9bd8ceabccaf · outbound

This paper cites If the entity is recognized, the assistant should bypass image search and directly use web_search(query).

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning If the entity is recognized, the assistant should bypass image search and directly use web_search(query)

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe9fbdf-5b64-459f-82a3-6a08e9fe8901 · outbound

This paper cites name": "<function-name>.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning name": "<function-name>

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44fa59a7-6518-4dab-beba-d9a376fe410e · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77b3c7f5-a9af-4177-a9e2-037999aace07 · outbound

This paper cites Near- duplicate queries are not considered useful additional evidence.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Near- duplicate queries are not considered useful additional evidence

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d37b0f34-741e-4f14-8e18-6393eb1afd9c · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b9faa9f-a714-494a-a164-067e027e1f5d · outbound

This paper cites Figure 12.System prompt for VideoSearcher reasoning with video navigation, external knowledge retrieval, and strict tool-use constraints.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Figure 12.System prompt for VideoSearcher reasoning with video navigation, external knowledge retrieval, and strict tool-use constraints

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4f59d39-ddc1-46b1-80f3-39d23606d91b · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab7834db-644f-417f-9747-05b273eb9b98 · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3859cdf0-4323-4d34-8c38-58a178c5cd2d · outbound

This paper cites 5.Multiple-choice Questions: For multiple-choice questions, the final answer must contain only the option letter.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning 5.Multiple-choice Questions: For multiple-choice questions, the final answer must contain only the option letter

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 529200a7-3397-4815-9beb-b67be1e2697f · outbound

This paper cites Output Format.The assistant may include brief reasoning in <think></think>, followed by the final answer in <answer></answer>.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Output Format.The assistant may include brief reasoning in <think></think>, followed by the final answer in <answer></answer>

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 343870df-7d4b-4151-8ab8-6f69195787d0 · outbound

This paper cites an unresolved cited work.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Unresolved cited work

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efcd8ed3-00d6-4353-ac94-e28227ea1667 · outbound

This paper cites name": "<function-name>.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning name": "<function-name>

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ce5e0a-06ef-40b1-8e1a-bd64a9db0c9e · outbound

This paper cites 3.Multiple-choice Questions: For multiple-choice questions, the final answer must contain only the option letter.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning 3.Multiple-choice Questions: For multiple-choice questions, the final answer must contain only the option letter

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5e35574-875b-4e4c-ba0b-741da3f2994f · outbound

This paper cites Output Format.The assistant may include brief reasoning in <think></think>, followed by the final answer in <answer></answer>.

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning Output Format.The assistant may include brief reasoning in <think></think>, followed by the final answer in <answer></answer>

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-12T06:04:16.637378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers