Home / AI Research / NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding
NEAI Research
NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding
by nex-agi · Tianci Xie, Li Chen, Pinxue Guo, Rui Zheng
Fine-grained questions about long videos ask how many times an action occurs, in what order events unfold, or exactly when a state changes. Answering them can require finding brief moments scattered across hours of footage. Agentic models that decide when and where to look promise to find these moments, yet this ability is hard both to measure and to learn. Sparse supporting evidence may establish that an action occurred without establishing its total count; verifying timeline-wide claims requires checking for missed occurrences and double counting. Answer-only supervision, in turn, does not explicitly supervise the search for evidence. We present NexSight, which builds verifiable tasks to…
Upvotes5
Comments2
Published16 Nov 2026
More from nex-agi
| NENex-N2.6AI Model APIs · #14 | $0.12 / $0.40 |
| NENex-N2.5-MiniAI Model APIs · #92 | $0.025 / $0.10 |
| NENex-N2.5-ProAI Model APIs · #93 | $0.075 / $0.25 |