[2605.04065] Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
Skip to main content
Learn about arXiv becoming an independent nonprofit.
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors. Donate
> cs > arXiv:2605.04065
Help | Advanced Search
All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text
Search
GO
quick links
Login
Help Pages
About
-->
Computer Science > Computation and Language
arXiv:2605.04065 (cs)
[Submitted on 11 Apr 2026]
Title:Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
Authors:Yiming Huang, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu
View a PDF of the paper titled Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs, by Yiming Huang and 6 other authors
View PDF HTML (experimental)
Abstract:Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based methods often lack the capacity to adapt to the model's evolving reasoning capabilities during training. Therefore, these methods can misdirect policy optimization in the absence of ground-truth supervision. To address this issue, we introduce FREIA, a novel RL-based algorithm built on two key innovations: (1) Free Energy-Driven Reward (FER) adapts rewards to balance consensus and exploration based on the Free Energy Principle. (2) Adaptive Advantage Shaping (AAS) adaptively adjusts learning signals based on the statistical characteristics of sampled rewards. Empirical evaluations on nine datasets across three reasoning tasks showcase that FREIA outperforms other unsupervised RL-based baselines. Notably, in mathematical reasoning tasks, FREIA surpasses other methods by an average of 0.5 to 3.5 points in Pass@1 using the DeepSeek-R1-Distill-Qwen-1.5B model.
Comments: Accepted by ACL 2026
Subjects:
Computation and Language (cs.CL); Emerging Technologies (cs.ET); Machine Learning (cs.LG)
Cite as: arXiv:2605.04065 [cs.CL]
(or arXiv:2605.04065v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.04065
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Yiming Huang [view email] [v1] Sat, 11 Apr 2026 07:26:04 UTC (2,559 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs, by Yiming Huang and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.ET cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
About
Help
contact arXivClick here to contact arXiv Contact
subscribe to arXiv mailingsClick here to subscribe Subscribe
Copyright
Privacy Policy
Web Accessibility Assistance
arXiv Operational Status