CAViAR: Critic-Augmented Video Agentic Reasoning
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_ | 1866918138172407808 |
|---|---|
| author | Menon, Sachit Iscen, Ahmet Nagrani, Arsha Weyand, Tobias Vondrick, Carl Schmid, Cordelia |
| author_facet | Menon, Sachit Iscen, Ahmet Nagrani, Arsha Weyand, Tobias Vondrick, Carl Schmid, Cordelia |
| contents | Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such as LVBench, Neptune, and ActivityNet-RTL, show performance wanes for tasks requiring complex reasoning on videos as queries grow more complex and videos grow longer. In this work, we ask: can existing perception capabilities be leveraged to successfully perform more complex video reasoning? In particular, we develop a large language model agent given access to video modules as subagents or tools. Rather than following a fixed procedure to solve queries as in previous work such as Visual Programming, ViperGPT, and MoReVQA, the agent uses the results of each call to a module to determine subsequent steps. Inspired by work in the textual reasoning domain, we introduce a critic to distinguish between instances of successful and unsuccessful sequences from the agent. We show that the combination of our agent and critic achieve strong performance on the previously-mentioned datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07680 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAViAR: Critic-Augmented Video Agentic Reasoning Menon, Sachit Iscen, Ahmet Nagrani, Arsha Weyand, Tobias Vondrick, Carl Schmid, Cordelia Computer Vision and Pattern Recognition Machine Learning Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such as LVBench, Neptune, and ActivityNet-RTL, show performance wanes for tasks requiring complex reasoning on videos as queries grow more complex and videos grow longer. In this work, we ask: can existing perception capabilities be leveraged to successfully perform more complex video reasoning? In particular, we develop a large language model agent given access to video modules as subagents or tools. Rather than following a fixed procedure to solve queries as in previous work such as Visual Programming, ViperGPT, and MoReVQA, the agent uses the results of each call to a module to determine subsequent steps. Inspired by work in the textual reasoning domain, we introduce a critic to distinguish between instances of successful and unsuccessful sequences from the agent. We show that the combination of our agent and critic achieve strong performance on the previously-mentioned datasets. |
| title | CAViAR: Critic-Augmented Video Agentic Reasoning |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2509.07680 |