arXiv AI
Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 15
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
arXiv:2610.19424v1 Announce Type: new Abstract: LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reaso...
arXiv AI
Oct 9
AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
AgentHorizon is a benchmark comprising 1,373 computer‑use tasks with instruction‑trajectory pairs collected from 166 hours of human‑recorded activity across three operating systems. The benchmark uses a paired design that swaps instructions to create negative tasks, testing judges’ ability to distinguish successful trajectories from those that completed a similar but incompatible request. Eleven judges were evaluated, with GPT‑5.5 achieving the highest balanced accuracy of 80.9% on the full trajectory subset, while tool‑use benefits some models but harms others, revealing large variability in judges’ performance.
arXiv AI
Aug 5
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
arXiv:2608. 03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration.
arXiv Computer Vision
Sep 1
From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents
arXiv:2608.31005v1 Announce Type: new Abstract: Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurr...
arXiv Computer Vision
Sep 18
VideoResearcher: Self-Improving Tool Design for Long-Video Understanding
VideoResearcher is a training‑free, multi‑agent framework that autonomously designs, tests, and refines high‑impact tools for long‑video understanding. It operates through dual Solving and Evolving loops, analyzing tool‑use trajectories to identify gaps, coordinating specialized agents to develop and validate executable tools, and reusing evolved tools to improve evidence acquisition in subsequent reasoning. The approach achieves state‑of‑the‑art performance among self‑improving agents and approaches the human‑designed upper bound, demonstrating a paradigm that expands agent capabilities while reducing costly manual engineering.
arXiv Computer Vision
Sep 14
Online Video Agent Harness for Long Video Understanding
arXiv:2609.12818v1 Announce Type: new Abstract: Long video understanding often behaves like a visual needle-in-a-haystack problem: query-relevant evidence is sparsely distributed across long temporal...