SOURCE-LINKED INTELLIGENCE

From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurrence coverage, or must discriminate competing hypotheses---which can cause failure before substantive reasoning begins. Prescribing a fine-grained solution procedure for every question is not a satisfactory remedy, as it restricts autonomous exploration. We propose VESTA, a training-free long-video agent organized as a route-conditioned acquire--verify--consolidate loop. Before exploration, an intent router infers an evidence-acquisition policy-

Read original source ↗ Open in workspace

recordType

paper

region

Global