3 papers
cs.AI2026
Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest
Abigail O'Neill, Alan Zhu, Mihran Miroyan +2
Language Model (LM)-based agents remain largely untested in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-par…
cs.LG2025
How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
Parth Asawa, Alan Zhu, Abigail O'Neill +3
Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting. We introduce Advisor Models, a method…
cs.CY2025
ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation
Rose Niousha, Mihran Miroyan, Abigail O'Neill +4
Evaluating Artificial Intelligence (AI) tutor feedback before deployment requires anticipating student engagement, typically assessed through real interaction data. We introduce Pa…