An automated evolution framework improves video-question-answering agents distribution-by-distribution, raising macro accuracy from 38.44% to 51.47% on a new eight-domain benchmark.
Claude code
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
An automated evolution framework improves video-question-answering agents distribution-by-distribution, raising macro accuracy from 38.44% to 51.47% on a new eight-domain benchmark.