TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

LLM with Planning

81 点作者 mercat大约 2 年前

6 条评论

codersfocus大约 2 年前
Summary:<p>The paper introduces LLM+P, a framework that combines the strengths of classical planners with large language models (LLMs) to solve long-horizon planning problems. LLM+P takes in a natural language description of a planning problem, converts it into a PDDL file, leverages classical planners to find a solution, and then translates the solution back into natural language. The authors provide a set of benchmark problems and find that LLM+P is able to provide optimal solutions for most problems, while LLMs fail to provide even feasible plans for most problems. The paper suggests that LLM+P can be used as a natural language interface for giving tasks to robot systems. The authors also propose that classical planners can be another useful external module for improving the performance of downstream tasks of LLMs. The paper highlights the importance of providing context (i.e., an example problem and its corresponding problem PDDL) for in-context learning, and suggests future research directions to further extend the LLM+P framework.<p>PPDL: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Planning_Domain_Definition_Language" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Planning_Domain_Definition_Lan...</a>
i-use-nixos-btw大约 2 年前
I’m wondering what PDDL is for, in practical terms.<p>Planning, yes, but that’s a verb that casts a very wide net.<p>When might one write PDDL? Be it specific tasks, or industries it is used in - the examples I’ve found online all have a robotic theme, yet the idea seems much more general.<p>What do they do with it once they’ve written it?<p>What does it solve (as opposed to just having the existence of a file that outlines objects, predicates, actions etc)?
评论 #35741260 未加载
评论 #35737460 未加载
评论 #35737408 未加载
behnamoh大约 2 年前
I had a similar idea to convert LLM inputs into Lisp language. I was pleased to see the paper takes this approach.<p>The underlying idea, though, has been done before. Basically we know that LLMs can do better if instead of solving a problem on their own, they write a program that solves it (look up PAL).
评论 #35735691 未加载
sitkack大约 2 年前
There is a link in the paper to an introduction in PDDL which is incorrect, it should point to <a href="https:&#x2F;&#x2F;www.cs.toronto.edu&#x2F;~sheila&#x2F;2542&#x2F;s14&#x2F;A1&#x2F;introtopddl2.pdf" rel="nofollow">https:&#x2F;&#x2F;www.cs.toronto.edu&#x2F;~sheila&#x2F;2542&#x2F;s14&#x2F;A1&#x2F;introtopddl2....</a>
PaulHoule大约 2 年前
Sometimes i wonder if text generation could be formulated as a planning&#x2F;optimization problem and if that facility could solve embedded planning problems as a byproduct.
评论 #35741322 未加载
评论 #35735833 未加载
gdiamos大约 2 年前
How can you connect the results from the LLM into the planner? Do you build a parser? Do you fine-tune the LLM to adhere to a format that the planner understands?
评论 #35735735 未加载
评论 #35741750 未加载