LongVideoAgent: Multi-Agent Reasoning with Long Videos
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917167076737024 |
|---|---|
| author | Liu, Runtao Liu, Ziyi Tang, Jiaqi Ma, Yue Pi, Renjie Zhang, Jipeng Chen, Qifeng |
| author_facet | Liu, Runtao Liu, Ziyi Tang, Jiaqi Ma, Yue Pi, Renjie Zhang, Jipeng Chen, Qifeng |
| contents | Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent. Code and data will be shared at https://longvideoagent.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20618 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LongVideoAgent: Multi-Agent Reasoning with Long Videos Liu, Runtao Liu, Ziyi Tang, Jiaqi Ma, Yue Pi, Renjie Zhang, Jipeng Chen, Qifeng Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multiagent Systems Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent. Code and data will be shared at https://longvideoagent.github.io/. |
| title | LongVideoAgent: Multi-Agent Reasoning with Long Videos |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2512.20618 |