一种灵活的多智能体LLM-人类框架，用于快速的人类验证工具构建
A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building
AI总结：
该研究提出了一种灵活的多智能体框架，通过人类反馈和强化学习，实现快速的人类验证工具构建，适用于复杂迭代任务。
摘要：
我们介绍了CollabToolBuilder，一种灵活的多智能体LLM框架，具有专家在环（HITL）指导，能够迭代学习为目标任务创建工具，与人类意图和过程对齐，同时最小化任务/领域适应时间和人类反馈的捕捉时间。该架构通过四个专门的智能体（教练、编码器、批评者、资本化器）生成并验证工具，使用强化动态提示和系统化的人类反馈整合来强化每个智能体在目标和约束下的角色。这项工作最佳视为一个系统层面的整合和方法，结合了多智能体上下文学习、HITL控制和可重用的工具资本化，用于复杂的迭代问题，如科学文档生成。我们通过初步实验（例如，根据摘要生成最新研究论文或专利）来说明它，并讨论其在其他迭代问题解决中的适用性。
英文摘要：
We introduce CollabToolBuilder, a flexible multiagent LLM framework with expert-in-the-loop (HITL) guidance that iteratively learns to create tools for a target goal, aligning with human intent and process, while minimizing time for task/domain adaptation effort and human feedback capture. The architecture generates and validates tools via four specialized agents (Coach, Coder, Critic, Capitalizer) using a reinforced dynamic prompt and systematic human feedback integration to reinforce each agent's role toward goals and constraints. This work is best viewed as a system-level integration and methodology combining multi-agent in-context learning, HITL controls, and reusable tool capitalization for complex iterative problems such as scientific document generation. We illustrate it with preliminary experiments (e.g., generating state-of-the-art research papers or patents given an abstract) and discuss its applicability to other iterative problem-solving.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
