PPL
Jie Gao
Papers (6)
Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative AnalysisMixture of Complementary Agents for Robust LLM EnsembleFORGE: Self-Evolving Agent Memory With No Weight Updates via Population BroadcastContext, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDPCan Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric StudyHow to Interpret Agent Behavior