arXiv · NLP· Dingwei Zhu, Jiahan Li, Chengjun Pan, Yunxian Yang, Yunbin Zhao, Yunke Zhang, Zhonghang Lu, Zhuohui Sheng, Chenhao Huang, Jiahang Lin, Yajie Yang, Junlin Shang, Shichun Liu, Yuhui Wang, Honglin Guo, Junjie Ye, Xin Guo, Jiazheng Zhang, Ming Zhang, Shihan Dou, Zhiheng Xi, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang·· 2026-10-15AI 评分23
IACM-RL:动态意图波动下复杂工具调用的意图感知上下文管理与强化学习
IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations
AI 导读
针对动态用户意图噪声导致的工具调用意图偏差及 API 重复循环问题,IACM-RL 框架提出 DynamicIntent 数据管道与 BeliefState 自生成上下文管理器,主动追踪目标变化并隔离被覆盖参数。
来源:arXiv · NLP · arxiv.org