聚焦LLM对话代理在数据库故障时的安全恢复策略，SIGDIAL 2026录用论文。
arXiv:2606.31307v1 Announce Type: new Abstract: Large language models used in task-oriented dialogue often produce fluent but unsafe responses when ba…
通过任务导向的随机化方法，有效提升黑盒算法的稳定性，为机器学习优化提供新思路。
arXiv:2606.25269v1 Announce Type: cross Abstract: As black-box models become foundational to modern research, ensuring their stability is paramount fo…
提出奖励引导解码框架，让预训练模型无需参数更新即可激发面向任务行为，补齐评估环节的缺失拼图。
arXiv:2605.28020v1 Announce Type: new Abstract: With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-t…
让保守的LLM在任务对话中主动出击，论文用奖励塑造RL解锁销售场景的前瞻策略。
arXiv:2605.22240v1 Announce Type: new Abstract: Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that active…