Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory
Agentic video understanding equips models with long-term memory to autonomously process and respond to continuous, long-horizon multimodal streams. However, advanced video agents often rely on ``detective-style'' iterative reasoning for action control (e.g., $\mathtt{search}$) and evidence aggregation, incurring prohibitive costs and latency. We argue that such heavy reasoning primarily compensates for the lack of global context and semantic misalignment in retrieval. This paper introduces Light-Omni, a multimodal agent framework for reflexive and lightweight video understanding. It achieves this through dual contextual states that instantly build the required context in a single forward ...
| Authors | Chang Nie, Jiaju Wei, Junlan Feng et al. |
|---|---|
| Primary category | cs.CV |
| Published | 6 July 2026 |
| Last updated at source | 6 July 2026 |
Connected in the knowledge graph
- ClareNie/Light-Omni-TrainingDataset · cited by
Models and datasets referencing this paper
- ClareNie/Light-Omni-TrainingDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.