PPL
Aojie Yuan
Papers (5)
AgentIR: A Workload-Adaptive Cascade Retrieval Substrate for Long-Term Conversational MemoryWhen Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use AgentsHidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not CausalBeyond Language: Format-Agnostic Reasoning Subspaces in Large Language ModelsNot All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning