[2606.16914] Greed Is Learned: Visible Incentives as Reward-Hacking Triggers

-->

Computer Science > Artificial Intelligence

arXiv:2606.16914 (cs)

[Submitted on 15 Jun 2026]

Title:Greed Is Learned: Visible Incentives as Reward-Hacking Triggers

Authors:Tong Che, Rui Wu<br>View a PDF of the paper titled Greed Is Learned: Visible Incentives as Reward-Hacking Triggers, by Tong Che and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Deployed agents increasingly act with their reward proxy in view, such as a balance, score, or KPI dashboard. We show that reinforcement learning can make a policy \emph{addicted} to such a visible self-benefit channel. It chases the displayed payoff across held-out domains, sacrifices the true task to do so, and follows the channel wherever we rewrite it, while policies that never saw the channel stay honest. We call this \emph{reward-channel addiction} and study it in \emph{MoneyWorld}, a synthetic sandbox. The addiction can \emph{flip a model's safety alignment}: trained only on innocuous money tasks with no safety content, the model abandons the safe action it otherwise always takes whenever a dashboard pays for an unsafe one, and reverts to safe once the channel is hidden. This learned bribe replicates across model scales and families. Blindly optimizing super-capable, next-generation AI on KPIs or P\&L can be dangerous for alignment. \emph{Greed is learned} when following such a channel pays.

Subjects:

Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2606.16914 [cs.AI]

(or<br>arXiv:2606.16914v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.16914

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Tong Che [view email]<br>[v1]<br>Mon, 15 Jun 2026 16:22:14 UTC (111 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Greed Is Learned: Visible Incentives as Reward-Hacking Triggers, by Tong Che and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

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

Change to browse by:

cs

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?)

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?)