arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.19667cs.AI
收藏

现实世界规划中的智能语言代理

Smart Language Agents in Real-World Planning

Pacific Collegiate School(太平洋学院);Saratoga High School(萨拉托加高中)

Annabelle Miin, Timothy Wei

AI总结:

研究提出结合LLM自动化提示与“human-in-the-loop”的半自动化提示生成框架,优化旅行规划代理的“sole-planning”能力,单次迭代使性能提升139%。

摘要:

综合规划代理一直是人工智能领域的长期目标。自然语言处理领域的近期创新通过大型语言模型(LLMs)的出现取得了成功。我们旨在通过扩展先前论文TravelPlanner的工作,提升此类LLMs的旅行规划能力。我们的目标是探索使用LLMs的新方法以改善旅行规划体验。我们特别关注旅行规划的“sole-planning”模式;即代理获得必要的参考信息,其目标是从参考信息中创建综合计划。虽然这并未模拟真实世界,但我们认为优化旅行规划代理的sole-planning能力仍能提升整体用户体验。我们提出了一种半自动化提示生成框架,该框架结合了LLM自动化提示和“human-in-the-loop”,以迭代方式优化提示从而提升LLM性能。结果显示,LLM自动化提示存在局限性,而“human-in-the-loop”在单次迭代中将性能提升了$139\%$。

英文摘要:

Comprehensive planning agents have been a long term goal in the field of artificial intelligence. Recent innovations in Natural Language Processing have yielded success through the advent of Large Language Models (LLMs). We seek to improve the travel-planning capability of such LLMs by extending upon the work of the previous paper TravelPlanner. Our objective is to explore a new method of using LLMs to improve the travel planning experience. We focus specifically on the "sole-planning" mode of travel planning; that is, the agent is given necessary reference information, and its goal is to create a comprehensive plan from the reference information. While this does not simulate the real-world we feel that an optimization of the sole-planning capability of a travel planning agent will still be able to enhance the overall user experience. We propose a semi-automated prompt generation framework which combines the LLM-automated prompt and "human-in-the-loop" to iteratively refine the prompt to improve the LLM performance. Our result shows that LLM automated prompt has its limitations and "human-in-the-loop" greatly improves the performance by $139\%$ with one single iteration.

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。

↑