1
Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents
LLM代理在信息获取中如何权衡成本与不确定性？新研究提出“校准-然后行动”方法，解决何时停止探索并提交答案的难题。
arXiv:2602.16699v3 Announce Type: replace Abstract: LLM agents are deployed in environments where they must interact to acquire information. In these …