Conference paper · 2025 · Open access
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
neural information processing systems, 119924–119988 · Published 1 January 2025 · DOI 10.52202/085713-3613
In brief
“Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models” is a 2025 conference paper by Yulei Qin and 8 co-authors, published in neural information processing systems. OpenAlex counts 22 citations as of 15 November 2026, which puts it in the top 4% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 22
- Most cited in
- 2026 (18)
- Field-weighted impact
- 7.75
- References
- 72
- Authors
- 9
Abstract
Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely chain-of-thought (CoT), is expected to universally improve capabilities of LLMs. However, we find that the vanilla CoT exerts a negative impact on performance due to its superficial reasoning pattern of simply paraphrasing the instructions. It fails to peel back the compositions of constraints for identifying their relationship across hierarchies of types and dimensions. To this end, we propose RAIF, a systematic method to boost LLMs in dealing with complex instructions via incentivizing reasoning for test-time compute scaling. First, we stem from the decomposition of complex instructions under existing taxonomies and propose a reproducible data acquisition method. Second, we exploit reinforcement learning (RL) with verifiable rule-centric reward signals to cultivate reasoning specifically for instruction following. We address the shallow, non-essential nature of reasoning under complex instructions via sample-wise contrast for superior CoT enforcement. We also exploit behavior cloning of experts to facilitate steady distribution shift from fast-thinking LLMs to skillful reasoners. Extensive evaluations on seven comprehensive benchmarks confirm the validity of the proposed method, where a 1.5B LLM achieves 11.74% gains with performance comparable to a 8B LLM. Evaluation on OOD constraints also confirms the generalizability of our RAIF. Codes and data are available at https://github.com/yuleiqin/RAIF. Keywords: reinforcement learning with verifiable rewards (RLVR), instruction following, complex instructions
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Qin, Y., Li, G., Li, Z., Xu, Z., Shi, Y., Lin, Z., Cui, X., Li, K., & Sun, X. (2025). Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models. neural information processing systems, 119924–119988. https://doi.org/10.52202/085713-3613
MLA 9
Qin, Yulei, et al. “Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models.” neural information processing systems, 2025, pp. 119924–119988. https://doi.org/10.52202/085713-3613.
Chicago
Qin, Yulei, Gang Li, Zongyi Li, Zihan Xu, Yuchen Shi, Zhekai Lin, Xiao Cui, Ke Li, and Xing Sun. 2025. “Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models.” neural information processing systems: 119924–119988. https://doi.org/10.52202/085713-3613.
Harvard
Qin, Y. et al. (2025) ‘Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models’, neural information processing systems, pp. 119924–119988. doi:10.52202/085713-3613.
IEEE
Y. Qin et al., “Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models,” neural information processing systems, pp. 119924–119988, 2025, doi: 10.52202/085713-3613.
BibTeX
@inproceedings{qin2025incentivizing,
title = {{Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models}},
author = {Qin, Yulei and Li, Gang and Li, Zongyi and Xu, Zihan and Shi, Yuchen and Lin, Zhekai and Cui, Xiao and Li, Ke and Sun, Xing},
booktitle = {neural information processing systems},
year = {2025},
pages = {119924--119988},
doi = {10.52202/085713-3613},
url = {https://doi.org/10.52202/085713-3613}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- instruction following
- large language models
- chain-of-thought
- Complex Instruction
- reinforcement learning with verifiable rewards
- reward function design
- behavior cloning
- test-time compute scaling
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Qin, Y., Li, G., Li, Z., Xu, Z., Shi, Y., Lin, Z., Cui, X., Li, K., & Sun, X. (2025). Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models. neural information processing systems, 119924–119988. https://doi.org/10.52202/085713-3613
How many times has this paper been cited?
22 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Yulei Qin, Gang Li, Zongyi Li, Zihan Xu, Yuchen Shi, Zhekai Lin, Xiao Cui, Ke Li, Xing Sun.
What is the DOI of this paper?
10.52202/085713-3613. The permanent link is https://doi.org/10.52202/085713-3613.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.