paper-with-me

홈 › Papers

Asking the Right Questions: Improving Reasoning with Generated Stepping Stones

2026-02-22 · Hengyuan Hu, Tingchen Fu, Minqi Jiang, Alexander H Miller, Yoram Bachrach, Jakob Nicolaus Foerster arxiv

Recent years have witnessed tremendous progress in enabling LLMs to solve complex reasoning tasks such as math and coding. As we start to apply LLMs to harder tasks that they may not be able to solve in one shot, it is worth paying attention to their ability to construct intermediate stepping stones that prepare them to better solve the tasks. Examples of stepping stones include simplifications, alternative framings, or subproblems. We study properties and benefits of stepping stones in the context of modern reasoning LLMs via ARQ (Asking the Right Questions), a simple framework that introduces a question generator to the default reasoning pipeline. We first show that good stepping stone questions exist and are transferrable, meaning that good questions can be generated, and they substantially help LLMs of various capabilities in solving the target tasks. We next frame stepping stone generation as a post-training task and show that we can fine-tune LLMs to generate more useful stepping stones by SFT and RL on synthetic data.

📄 PDF Abstract BibTeX arXiv:2602.19069

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Asking Complex Questions with Multi-hop Answer-focused Reasoning

2020-09-16 · Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li 외

Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant words from the i…

Question GenerationQuestion-Generation

Are You Asking the Right Questions? Teaching Machines to Ask Clarification Questions

2017-07-01 · ACL 2017 7 · Sudha Rao

A Feasibility Study of Answer-Unaware Question Generation for Education

2022-05-01 · Findings (ACL) 2022 5 · Liam Dugan, Eleni Miltsakaki, Shriyash Upadhyay, Etan Ginsberg 외

We conduct a feasibility study into the applicability of answer-unaware question generation models to textbook passages. We show that a significant portion of errors in such systems arise from asking irrelevant or un-int…

Question GenerationQuestion-Generation

A Feasibility Study of Answer-Agnostic Question Generation for Education

2022-03-16 · Liam Dugan, Eleni Miltsakaki, Shriyash Upadhyay, Etan Ginsberg 외

We conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages. We show that a significant portion of errors in such systems arise from asking irrelevant or unint…

Question GenerationQuestion-Generation

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

2025-06-10 · David Acuna, Ximing Lu, JaeHun Jung, Hyunwoo Kim 외

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 distilla…

Visual Reasoning