PPL
Yixin Cao
Papers (4)
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy PrefixesSkill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM AgentsOpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM AgentsSliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning