Summary of Robust Planning with Llm-modulo Framework: Case Study in Travel Planning, by Atharva Gundawar et al.
Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning
by Atharva Gundawar, Mudit Verma, Lin Guan, Karthik Valmeekam, Siddhant Bhambri, Subbarao Kambhampati
First submitted to arxiv on: 31 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper explores the potential of Large Language Models (LLMs) to excel in planning and reasoning tasks, traditionally reserved for System 2 cognitive competencies. The authors propose a conceptual framework that enhances LLM integration into diverse planning and reasoning activities. Specifically, they apply this framework to travel planning using the Travel Planning benchmark by the OSU NLP group. Unlike popular methods like Chain of Thought, ReAct, and Reflexion, which achieve meager results with GPT3.5-Turbo (0%, 0.6%, and 0%, respectively), their operationalization of LLM-Modulo framework for TravelPlanning domain provides a significant improvement, enhancing baseline performances by 4.6x for GPT4-Turbo and even more for older models like GPT3.5-Turbo from 0% to 5%. Additionally, they highlight the other useful roles of LLMs in the planning pipeline, as suggested in LLM-Modulo, such as extraction of useful critics and reformulator for critics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models (LLMs) are super smart computers that can help us with lots of tasks. Right now, people are trying to figure out how to use them for special jobs like planning and reasoning. Planning is when we make a plan for something, like a trip. Reasoning is when we think about why something makes sense or not. The paper talks about a new way to use LLMs for planning that works really well. They tested it with travel planning and showed that it can do much better than other ways that people have tried. |
Keywords
» Artificial intelligence » Nlp
