Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy

Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in LLMs. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}. Existing paradigms, driven by text-centric outcome rewards, reasoning in language medium, inadvertently encourage models to bypass visual perception. We empirically validate this through blind experiments: state-of-the-art policies maintain or surprisingly improve performance even when visual inputs are entirely removed. This reveals that these models degenerate into \textit{blind reasoners}, exploiting linguistic priors to generate plausible answers instead of attending to visual evidence. In response, we propose \textbf{Thinking with Deltas}, a framework driven by a \textbf{Differential Visual Reasoning Policy (DVRP)}. DVRP introduces intrinsic supervision via visual triplets, comprising original, masked, and perturbed inputs. It optimizes the model to maximize reasoning divergence from masked inputs (enforcing \textit{visual sensitivity}) while minimizing divergence from perturbed inputs (ensuring \textit{visual robustness}). By aligning reasoning variations strictly with the \textit{Delta} of visual information, DVRP inherently bolsters visual understanding capabilities and significantly outperforms state-of-the-art methods on both general and medical benchmarks, without requiring external annotations or auxiliary tools.