Generalized Planning in PDDL Domains with Pretrained Large Language Models · HackerPapers discussions

Generalized Planning in PDDL Domains with Pretrained Large Language Models — mentioned by YeGoblynQueenne

Sun, 12 May 2024 11:13:14 GMT

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 with CoT summarization and automated debugging is a surprisingly strong generalized planner in PDDL domains. The author of the tweet is an expert on planning and he's responding to that kind of thing.

Paper and discussion history. A mention is not an endorsement.

Generalized Planning in PDDL Domains with Pretrained Large Language Models — mentioned by openquery

Mon, 27 Nov 2023 15:34:41 GMT

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 olympiad problem into a form suitable for a theorem prover? [0] https://arxiv.org/pdf/2305.11014.pdf

Paper and discussion history. A mention is not an endorsement.