paper-with-me

홈 › Papers

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

2025-06-10 · David Acuna, Ximing Lu, JaeHun Jung, Hyunwoo Kim, Amlan Kar, Sanja Fidler, Yejin Choi

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.

📄 PDF Abstract BibTeX arXiv:2506.08927

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Reasoning

Similar Papers 제목 키워드 기반

SSR: Socratic Self-Refine for Large Language Model Reasoning

2025-11-13 · Haizhou Shi, Ye Liu, Bo Pang, Zeyu Leo Liu 외 arxiv

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limiting their effectiveness on complex tasks. …

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models

2023-05-24 · Jingyuan Qi, Zhiyang Xu, Ying Shen, Minqian Liu 외

Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. However, confined by its inherent single-pass and sequential generation process, CoT he…

Language ModellingMathMMLUQuestion Answering+1

Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns

2025-05-29 · Xiang Li, Haiyang Yu, Xinghua Zhang, Ziyang Huang 외

Process Reward Models (PRMs) are crucial in complex reasoning and problem-solving tasks (e.g., LLM agents with long-horizon decision-making) by verifying the correctness of each intermediate reasoning step. In real-world…

Benchmarking

MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation

2025-02-18 · Yutong Wang, Pengliang Ji, Chaoqun Yang, Kaixin Li 외

The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scali…

global-optimizationLarge Language Model

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction

2026-02-03 · Zhengbo Jiao, Shaobo Wang, Zifan Zhang, Wei Wang 외 arxiv

Multimodal Large Language Models (MLLMs) have significantly advanced vision-language understanding. However, even state-of-the-art models struggle with geometric reasoning, revealing a critical bottleneck: the extreme sc…

Synthetic Data GenerationImage Generation