按年被提到
20232023 · 1 次2026
大模型与语言模型›大模型推理与思维链·arXiv:2305.11014 · cs.AI

Generalized Planning in PDDL Domains with Pretrained Large Language Models

Tom Silver, Soham Dan, Kavitha Srinivas, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Michael Katz · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-11-27 · 最近 2024-05-12
2不同的人
2活跃月份
2讨论串
90被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain. In particular, we consider PDDL domains and use GPT-4 to synthesize Python programs. We also consider (1) Chain-of-Thought (CoT) summarization, where the LLM is prompted to summarize the domain and propose a strategy in words before synthesizing the program; and (2) automated debugging, where the program is validated with respect to the training tasks, and in case of errors, the LLM is re-prompted with four types of feedback. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. Overall, we find that GPT-4 is a surprisingly powerful generalized planner. We also conclude that automated debugging is very important, that CoT summarization has non-uniform impact, that GPT-4 is far superior to GPT-3.5, and that just two training tasks are often sufficient for strong generalization.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论openquery · 2023-11

“Can automated theorem provers solve mathematical olympiad problems in a reasonable time given enough compute? LLMs are quite good at generating semantically correct language. I remember reading a paper about extending the planning capabilities of GPT-4 by using a Planning Domain Definition Language [0]. By that same logic could an LLM not translate the o…”

$10M AI Mathematical Olympiad Prize原评论 ↗
评论YeGoblynQueenne · 2024-05

“From the tweet: >> And yet the practitioners of CoT swear that any and every problem can be solved with LLM by giving it a bit of a CoT help. For example, see this arxiv paper: Generalized Planning in PDDL Domains with Pretrained Large Language Models https://arxiv.org/abs/2305.11014 Where the authors conclude: In this work, we showed that GPT-4 wit…”

The "Chain of Thought" Delusions原评论 ↗