PPL
Dongha Lee
Papers (5)
Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMsPersonalizing Embodied Multimodal Large Language Model Agents over Long-term User InteractionsPAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent OptimizationRegion4Web: Rethinking Observation Space Granularity for Web AgentsOPSD Compresses What RLVR Teaches: A Post-RL Compaction Stage for Reasoning Models