SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation Reliability 文章

ArXiv CS.CL2026-05-27NEWSen作者: Ramakrishna Vamsi Setti, Jagadeesh Rachapudi, Sachin Chaudhary, Praful Hambarde, Amit Shukla

大语言模型

查看原文 →

SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation Reliability · 相关技术

相关技术

ORM ODE LLM language model 远程代码执行（RCE）rsa reinforcement learning UCT TURN Layout-as-Policy LMM large language models HIS For DiT CIS ARG ANN