# Think in 360°: Benchmarking and Bootstrapping Panoramic Video Reasoning

**Authors:** Lidong Lu, Lidong Zou, Xinyi Mao, Jiaxin Lv, Zhenquan Li, Liangrui Dong, Tong Lu, Guo Chen  
**Lab:** Nanjing University · **Published:** 30 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.42082) · [PDF](https://arxiv.org/pdf/2610.42082) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.42082.html)

## Key numbers

- **55.7%**: It reaches 55.7% on PanoVideoBench
- **1,000**: Its 1,000 questions span five categories and 15 question types
- **13,465**: through sphere-time-grounded synthesis that converts verified panoramic observations and successful agentic explorations into 13,465 QA-CoT pairs

## Abstract

A panoramic video captures all directions around the camera, but relevant evidence can appear in different directions and at different times. Understanding it requires models to connect observations across the viewing sphere and time. We introduce PanoVideoBench, the first manually annotated benchmark for comprehensive panoramic video understanding. Its 1,000 questions span five categories and 15 question types, with diagnostic annotations for target search and panoramic capabilities. Evaluation of 11 proprietary, open-source, and panoramic-specialized models identifies cross-view tracking and sphere-time evidence integration as their weakest capabilities. To strengthen these capabilities, we construct PanoVideoCoT, the first reasoning dataset grounded in real panoramic video, through sphere-time-grounded synthesis that converts verified panoramic observations and successful agentic explorations into 13,465 QA-CoT pairs. Starting from a general video MLLM, PanoVideoReasoner learns from this corpus through Panoramic CoT SFT and Evidence-Privileged On-Policy Self-Distillation, a panoramic instantiation of Vision-OPD's OPSD in which the teacher uses verified perspective views to guide student-generated trajectories. It reaches 55.7% on PanoVideoBench, improving the backbone by 12.5 points and the previous SOTA by 2.6. The gains concentrate on the same spatial, cross-view, and temporal capabilities exposed by the benchmark, showing that grounded sphere-time supervision can equip a general video MLLM with panoramic reasoning.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.