Conference paper · 2026 · Open access

Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs

Yiming Huang, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu

Proceedings of the conference - Association for Computational Linguistics. Meeting, 17540–17560 · Published 1 January 2026 · DOI 10.18653/v1/2026.acl-long.797

Free PDFView at the publisherCite this paper

In brief

“Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs” is a 2026 conference paper by Yiming Huang and 6 co-authors, published in Proceedings of the conference - Association for Computational Linguistics. Meeting. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at Proceedings of the conference - Association for Computational Linguistics. Meeting.

Citations
0
References
20
Authors
7

Abstract

Yiming Huang, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Huang, Y., Shi, Z., Wen, X.-C., Zeng, J., Gao, C., Han, P., & Liu, C. (2026). Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs. Proceedings of the conference - Association for Computational Linguistics. Meeting, 17540–17560. https://doi.org/10.18653/v1/2026.acl-long.797

MLA 9

Huang, Yiming, et al. “Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs.” Proceedings of the conference - Association for Computational Linguistics. Meeting, 2026, pp. 17540–17560. https://doi.org/10.18653/v1/2026.acl-long.797.

Chicago

Huang, Yiming, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng, Cuiyun Gao, Peiyi Han, and Chuanyi Liu. 2026. “Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs.” Proceedings of the conference - Association for Computational Linguistics. Meeting: 17540–17560. https://doi.org/10.18653/v1/2026.acl-long.797.

Harvard

Huang, Y. et al. (2026) ‘Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs’, Proceedings of the conference - Association for Computational Linguistics. Meeting, pp. 17540–17560. doi:10.18653/v1/2026.acl-long.797.

IEEE

Y. Huang et al., “Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs,” Proceedings of the conference - Association for Computational Linguistics. Meeting, pp. 17540–17560, 2026, doi: 10.18653/v1/2026.acl-long.797.

BibTeX

@inproceedings{huang2026free,
  title     = {{Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs}},
  author    = {Huang, Yiming and Shi, Zhenbo and Wen, Xin-Cheng and Zeng, Jichuan and Gao, Cuiyun and Han, Peiyi and Liu, Chuanyi},
  booktitle = {Proceedings of the conference - Association for Computational Linguistics. Meeting},
  year      = {2026},
  pages     = {17540--17560},
  doi       = {10.18653/v1/2026.acl-long.797},
  url       = {https://doi.org/10.18653/v1/2026.acl-long.797}
}

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

  • free energy principle
  • reinforcement learning
  • large language models
  • self-supervised learning
  • language model fine-tuning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Huang, Y., Shi, Z., Wen, X.-C., Zeng, J., Gao, C., Han, P., & Liu, C. (2026). Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs. Proceedings of the conference - Association for Computational Linguistics. Meeting, 17540–17560. https://doi.org/10.18653/v1/2026.acl-long.797

How many times has this paper been cited?

0 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 Proceedings of the conference - Association for Computational Linguistics. Meeting.

Who wrote this paper?

Yiming Huang, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu.

What is the DOI of this paper?

10.18653/v1/2026.acl-long.797. The permanent link is https://doi.org/10.18653/v1/2026.acl-long.797.

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.