SOURCE-LINKED INTELLIGENCE

Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-scale iterations on a self-contained program. Online autoresearch instead spans asynchronous systems, hours-long variants, and weeks-long campaigns that can influence a product. A completed run can still support an invalid conclusion when a code change is a no-op, data windows leak, evaluator semantics drift, or the two arms traverse different serving funnels. We present EvoPilot, a human-gated method for long-horizon online autoresearch. Role-spe

Read original source ↗ Open in workspace

recordType

paper

region

Global