Summary of Query-efficient Planning with Language Models, by Gonzalo Gonzalez-pumariega et al.
Query-Efficient Planning with Language Models
by Gonzalo Gonzalez-Pumariega, Wayne Chen, Kushal Kedia, Sanjiban Choudhury
First submitted to arxiv on: 9 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
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 proposes and studies two frameworks that leverage Large Language Models (LLMs) for query-efficient planning in complex environments. The first framework uses LLMs as a heuristic within a search-based planner to select promising nodes to expand and propose actions, while the second framework uses LLMs as a generative planner to propose an entire sequence of actions from start to goal and adapt based on feedback. The paper shows that both approaches improve upon comparable baselines, but using an LLM as a generative planner results in significantly fewer interactions. The key finding is that the LLM as a planner can more rapidly adapt its planning strategies based on immediate feedback than LLM as a heuristic. The paper presents evaluations and ablations on Robotouille and PDDL planning benchmarks and discusses connections to existing theory on query-efficient planning algorithms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores how Large Language Models (LLMs) can help with planning in complex environments. It proposes two ways that LLMs can be used for planning: as a heuristic to choose which actions to take next, or as a planner that suggests an entire sequence of actions. The researchers tested these approaches and found that using the LLM as a planner is more efficient than using it as a heuristic. This means that the LLM can come up with good plans quickly, without needing to explore many possibilities. The paper also discusses how this work relates to other research on planning algorithms. |
