Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rana Muhammad Usman

Rana Muhammad Usman

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2NLP×2Crypto×2

Research Timeline

2026
Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

The paper demonstrates that the sequence and composition of external information (the 'feed') an LLM agent consumes can significantly and causally steer its final decisions, often overriding its default stance.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

The paper demonstrates that the order and content of external information (the 'feed') an LLM agent consumes before making a decision can significantly and causally steer its final choice, often overriding its default stance.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLcs.CRRecentMay 30, 2026

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

Rana Muhammad Usman

The paper demonstrates that the sequence and composition of external information (the 'feed') an LLM agent consumes can significantly and causally steer its final decisions, often overriding its defau…

View →
cs.AIcs.CLcs.CRRecentMay 30, 2026

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

Rana Muhammad Usman

The paper demonstrates that the order and content of external information (the 'feed') an LLM agent consumes before making a decision can significantly and causally steer its final choice, often overr…

View →