让AI团队协作写工具，人实时把关，省时高效。
A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building
- 四角色AI团队协作，人机闭环反馈生成工具
- 通过动态提示与反馈机制，精准匹配人类意图
- 适合科研论文、专利等需反复迭代的任务
我们提出CollabToolBuilder，一个灵活的多智能体大模型框架，结合专家在环（HITL）指导，通过迭代学习为特定目标构建工具，保持与人类意图和流程一致，同时最小化任务/领域适配时间和人工反馈收集成本。该架构通过四个专业化智能体（教练、编码员、评审员、资本化员）协同工作，采用强化动态提示和系统化的人类反馈整合，持续优化各智能体在目标与约束下的表现。本工作可视为多智能体上下文学习、人机闭环控制与可复用工具积累的系统级融合方法，适用于科学文档生成等复杂迭代问题。初步实验展示其在根据摘要生成前沿研究论文或专利方面的应用潜力，并讨论其在其他迭代式求解场景中的适用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。