[2606.04075] Large Language Models Hack Rewards, and Society

-->

Computer Science > Machine Learning

arXiv:2606.04075 (cs)

[Submitted on 2 Jun 2026 (v1), last revised 18 Jun 2026 (this version, v2)]

Title:Large Language Models Hack Rewards, and Society

Authors:Wei Liu, Xinyi Mou, Hanqi Yan, Zhongyu Wei, Yulan He<br>View a PDF of the paper titled Large Language Models Hack Rewards, and Society, by Wei Liu and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal regulations are structurally similar to reward functions. They define measurable outcomes, thresholds, and exceptions, while often leaving institutional intent only partially specified. We hypothesise that the RL training process may exploit these gaps and therefore ask whether models' well-known tendency to hack reward functions during RL can scale into a more consequential failure mode named societal hacking: discovering loopholes in the rules society runs on. To study this phenomenon, we introduce SocioHack, a sandbox of 72 societal environments, and find that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery. Models learn to hack the social rules and generate strategies that remain technically compliant while defeating regulatory intent, and current LLM safeguards provide only limited mitigation. Therefore, collecting in-the-wild feedback for model training requires greater caution, and we need a next-generation post-training paradigm for safely iterating LLMs in real society.=

Comments:<br>14 pages, 9 figures, 7 tables

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Cryptography and Security (cs.CR); Computers and Society (cs.CY)

Cite as:<br>arXiv:2606.04075 [cs.LG]

(or<br>arXiv:2606.04075v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.04075

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Wei Liu [view email]<br>[v1]<br>Tue, 2 Jun 2026 16:29:48 UTC (787 KB)

[v2]<br>Thu, 18 Jun 2026 13:14:32 UTC (865 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Large Language Models Hack Rewards, and Society, by Wei Liu and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs<br>cs.AI<br>cs.CL<br>cs.CR<br>cs.CY

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

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?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

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? |<br>Disable MathJax (What is MathJax?)