Summary of Thought Of Search: Planning with Language Models Through the Lens Of Efficiency, by Michael Katz et al.
Thought of Search: Planning with Language Models Through The Lens of Efficiency
by Michael Katz, Harsha Kokel, Kavitha Srinivas, Shirin Sohrabi
First submitted to arxiv on: 18 Apr 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 The paper investigates the properties of using large language models (LLMs) for planning, focusing on soundness, completeness, and complexity. Recent trends prioritize efficiency over these properties, leading to inefficient methods. The authors propose a more efficient approach that maintains both soundness and completeness, demonstrated through four representative search problems and comparisons with LLM-based solutions from the literature. The results show that using LLMs to produce code for search components can achieve 100% accuracy with only a few calls, emphasizing the importance of responsible compute resource usage. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how well large language models (LLMs) work when used for planning. Currently, many methods prioritize being fast over making sure they’re correct and complete. The authors suggest a new way to do this that’s both efficient and sound. They test their approach on four different problems and compare it to other methods that use LLMs. This shows that using LLMs can be really accurate with just a few tries, which is important for being responsible with computer power. |
