@inproceedings{acuna-etal-2025-socratic,
    title = "Socratic-{MCTS}: Test-Time Visual Reasoning by Asking the Right Questions",
    author = "Acuna, David  and
      Lu, Ximing  and
      Jung, Jaehun  and
      Kim, Hyunwoo  and
      Kar, Amlan  and
      Fidler, Sanja  and
      Choi, Yejin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1230/",
    pages = "24158--24171",
    ISBN = "979-8-89176-332-6",
    abstract = "Recent research in vision-language models (VLMs) has centered around the possibility of equipping them with implicit long-form chain-of-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 non-reasoning 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."
}