Routing by Reasoning Need: Trajectory-Aware Decoding Control for Diffusion Vision-Language Models

The paper introduces a routing-by-reasoning-need controller for diffusion vision‑language models that dynamically selects early commitment, baseline preservation, or reasoning‑supportive decoding based on trajectory signals such as answer closure, commitment evidence, and representation revision pressure. This training‑free approach avoids a single universal generation length, instead tailoring inference‑time control to the reasoning demands of each question. Experiments on answer‑focused, mixed‑reasoning, and chain‑of‑thought benchmarks show that routed control improves robustness compared to fixed long or short decoding and single‑rule interventions, with benefits not solely due to shorter outputs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• diffusion
• multimodal
• benchmarks