Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions

Recent research in vision-language models (VLMs) has centered around the possibility of equipping them with implicit long-form chainof-thought reasoning-akin to the success observed in language models-via distillation and reinforcement learning. But what about the non-reasoning models already trained and deployed across the internet? Should we simply abandon them, or is there hope for a search mechanism that can elicit hidden knowledge and induce long reasoning traces-without any additional training or supervision? In this paper, we explore this possibility using a Monte Carlo Tree Search (MCTS)-inspired algorithm, which injects subquestion-subanswer pairs into the model's output stream. We show that framing reasoning as a search process-where subquestions act as latent decisions within a broader inference trajectory-helps the model "connect the dots" between fragmented knowledge and produce extended reasoning traces in nonreasoning models. We evaluate our method across three benchmarks and observe consistent improvements. Notably, our approach yields a 2% overall improvement on MMMU-PRO, including a significant 9% gain in Liberal Arts. Problem (P) What is the position of the blue car in the image? A: parked on the sidewalk B: driving on the road C: parked on the grass D: parked on the road CoT: To determine the position of the blue car in the image, let's analyze the scene: * The image shows a busy urban street with several vehicles. * The blue car is located on the right side of the image. * It is positioned on what appears to be a paved surface, which is consistent with a road. * The car is not on the grass or the sidewalk, as those areas are clearly distinguishable in the image. * The car is stationary, suggesting it is parked. Given these observations, the blue car is parked on the road. Answer: D [Wrong]