Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.22139 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913170316066816 |
|---|---|
| author | Chen, Xin Jiang, Feng Zhang, Yiqian Chen, Hardy Yan, Shuo Xie, Wenya Yang, Min Huang, Shujian |
| author_facet | Chen, Xin Jiang, Feng Zhang, Yiqian Chen, Hardy Yan, Shuo Xie, Wenya Yang, Min Huang, Shujian |
| contents | Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a \emph{blind self-thinking} paradigm: performing extensive internal reasoning even when critical information is missing or ambiguous. We propose Proactive Interactive Reasoning (PIR), a new reasoning paradigm that transforms LLMs from passive solvers into proactive inquirers that interleave reasoning with clarification. Unlike existing search- or tool-based frameworks that primarily address knowledge uncertainty by querying external environments, PIR targets premise- and intent-level uncertainty through direct interaction with the user. PIR is implemented via two core components: (1) an uncertainty-aware supervised fine-tuning procedure that equips models with interactive reasoning capability, and (2) a user-simulator-based policy optimization framework driven by a composite reward that aligns model behavior with user intent. Extensive experiments on mathematical reasoning, code generation, and document editing demonstrate that PIR consistently outperforms strong baselines, achieving up to 32.70\% higher accuracy, 22.90\% higher pass rate, and 41.36 BLEU improvement, while reducing nearly half of the reasoning computation and unnecessary interaction turns. Further reliability evaluations on factual knowledge, question answering, and missing-premise scenarios confirm the strong generalization and robustness of PIR. Model and code are publicly available at: \href{https://github.com/SUAT-AIRI/Proactive-Interactive-R1} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22139 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers Chen, Xin Jiang, Feng Zhang, Yiqian Chen, Hardy Yan, Shuo Xie, Wenya Yang, Min Huang, Shujian Computation and Language Artificial Intelligence Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a \emph{blind self-thinking} paradigm: performing extensive internal reasoning even when critical information is missing or ambiguous. We propose Proactive Interactive Reasoning (PIR), a new reasoning paradigm that transforms LLMs from passive solvers into proactive inquirers that interleave reasoning with clarification. Unlike existing search- or tool-based frameworks that primarily address knowledge uncertainty by querying external environments, PIR targets premise- and intent-level uncertainty through direct interaction with the user. PIR is implemented via two core components: (1) an uncertainty-aware supervised fine-tuning procedure that equips models with interactive reasoning capability, and (2) a user-simulator-based policy optimization framework driven by a composite reward that aligns model behavior with user intent. Extensive experiments on mathematical reasoning, code generation, and document editing demonstrate that PIR consistently outperforms strong baselines, achieving up to 32.70\% higher accuracy, 22.90\% higher pass rate, and 41.36 BLEU improvement, while reducing nearly half of the reasoning computation and unnecessary interaction turns. Further reliability evaluations on factual knowledge, question answering, and missing-premise scenarios confirm the strong generalization and robustness of PIR. Model and code are publicly available at: \href{https://github.com/SUAT-AIRI/Proactive-Interactive-R1} |
| title | Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.22139 |