AI RESEARCH
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
arXiv CS.AI
•
ArXi:2407.03884v4 Announce Type: replace-cross Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their **lack of controllability** remains a key challenge, often leading to unfocused conversations or task failure. To address this, we