Rewarding Structural Conformance of Reasoning using Process Mining 文章

ArXiv CS.AI2026-05-26NEWSen作者: Yongjae Lee, Taekhyun Park, Sunghyun Sim, Hyerim Bae
查看原文 →
关系图谱

Rewarding Structural Conformance of Reasoning using Process Mining · 相关技术

相关技术

TTEODEPLAlanguage model远程代码执行（RCE）后训练reinforcement learningUCTStraight-Through EstimatorScalaSPAReferring expression comprehension (REC)Parts-of-Speech (POS) tagsOTAORMNarrative Abstraction BenchmarkMathematicaMITHISForEffort Metric AttentionENADiTANNCLEARTPU