Runtime Evaluation of PCG in Endless Runner Games
Explore runtime evaluation of procedural content generation in endless runner games using autonomous agents for balanced, playable levels.
Foresight-Guided Defense to Stop Infection in Multi-Agent AI
Discover how foresight-guided local purification defends multi-agent systems from infectious jailbreaks, reducing infection rates below 5.5%.
NH-CROP: Robust Pricing for Language Data Assets
Discover NH-CROP, a robust pricing framework for governed language data assets that handles cost uncertainty and optimizes revenue strategies.
Do LLMs Misjudge Entertainment News Credibility?
Explore how large language models differ in detecting fake news in entertainment vs. hard news and the impact on news credibility assessment.
Boost AI Trust with Route Receipts for Model Routing
Enhance AI transparency and trust with route receipts, a new method to track adaptive AI system routing and improve accountability.