Recent VLMs improve multimodal reasoning by generating explicit chains of thought, but often overthink with redundant reasoning. Although conventional length penalties mitigate this redundancy, they rely on coarse global rewards that fail to discern intermediate process quality or adapt to task complexity. To address this dilemma, we propose Binned Relative Policy Optimization (BRPO), a training-efficient framework that enables non-trivial process-level evaluation without introducing costly process reward models. Specifically, BRPO leverages high entropy lexical markers to segment reasoning trajectories into discrete intermediate prefixes, evaluating their problem-solving potential through forced answer completions. Building on this, we introduce Bin Normalization along with a length-aware adjustment to map prefixes into process bins, dynamically calibrating rewards and regulating length constraints based on reasoning stages and visual complexity. Experiments on six multimodal math benchmarks show that our method improves both accuracy and efficiency: on Qwen2.5-VL-7B, it raises average accuracy from 47.8% to 53.6% while reducing the average response length by 39.0%.

Radiologists read CT as a sequential decision process, actively scrolling, zooming, adjusting windows, comparing with prior scans, and measuring structures, where each observation guides the next action. Current VLMs instead answer from passively sampled views, missing the multi-step reasoning that clinical reading demands. We address this by aligning the agent’s action space to the radiologists’ operations within the Picture Archiving and Communication System (PACS), enabling active, multi-step CT reading with inherently transparent reasoning for clinical decision support. In particular, we build **ACTOR**, a unified framework comprising: (1) a PACS-like interactive CT environment with five radiologist-aligned tools; (2) **ActiveCTR-Bench**, spanning 7 tasks across a Perception–Interpretation–Reasoning hierarchy (7,112 items with visual ground truth and verified vision necessity); and (3) **ActiveCTReasoner**, a 7B model trained on 108K synthesized trajectories via SFT and reinforcement learning. ActiveCTReasoner achieves 73.2% close-ended accuracy, outperforming GPT-5.4 (47.3%) remarkably. In open-ended evaluations, it scores 44.2% compared to 23.8% for the best baseline. A radiologist collaboration study provides preliminary evidence for the decision-support utility of radiologist-aligned agentic reasoning.