5 papers
Runtime Action Interference for AI Control of AlphaStar in StarCraft II
Jaymari Chua, Chen Wang, Liming Zhu +1
A trained reinforcement learning policy does not determine the complete behavior that users encounter: deployment code still schedules, admits, suppresses, or replaces its proposed…
Three-Body Alignment: Aligning Chess Agent with Human Reasoning through Reranked Rationale
Jaymari Chua, Chen Wang, Liming Zhu +1
As reasoning agents become increasingly complex, aligning their underlying reasoning and decision-making processes with human conceptual models is a challenge for AI security and s…
Situation Perception: A Necessary Primitive to Artificial Superintelligence
Ziqin Yuan, Jaymari Chua
Current large language models are extraordinary statistical engines. They compress vast amounts of text into useful patterns and can explain science, write code, imitate reasoning,…
Superhuman Game AI Disclosure: Expertise and Context Moderate Effects on Trust and Fairness
Jaymari Chua, Chen Wang, Lina Yao
As artificial intelligence surpasses human performance in select tasks, disclosing superhuman capabilities poses distinct challenges for fairness, accountability, and trust. Howeve…
Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents
Jaymari Chua, Chen Wang, Lina Yao
Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Lea…