AdaTurn: Budget-Aware Test-Time Scaling for Active Visual Perception Agents
AdaTurn is a framework for active visual perception agents that enables them to adapt to varying rollout budgets by conditioning on the allowed number of turns and explicitly training for boundary behavior. Its Forced-Answer DAPO component turns over-budget events into trainable final-decision steps, allowing agents to synthesize answers even when further actions are not possible. The approach significantly improves low-budget accuracy and generalizes across different agent backbones and multimodal benchmarks.
Why it matters: AdaTurn addresses a key deployment challenge by enabling active visual agents to provide valid answers under varying and tight turn limits, improving their practical usability.
Full story at: arXiv Computer Vision ↗