2 papers
cs.CV2026
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
Wenqi Liu, Shijie Ma, Yunxiao Wang +21
Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While…
cs.CL2026
Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue
Junan Hu, Shudan Guo, Wenqi Liu +2
Large Language Models demonstrate outstanding performance in many language tasks but still face fundamental challenges in managing the non-linear flow of human conversation. The pr…