LLM+P: Empowering Large Language Models with Optimal Planning Proficiency · HackerPapers discussions

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency — mentioned by Animats

Tue, 02 May 2023 07:36:39 GMT

Raw large language models have no inner-monologue or meta-cognition. But there are various systems which bolt planning and sub-goal systems onto LLMs.[1][2] Those have self-generated work, where LLMs generate tasks for subsystems, which return data used by the LLMS to generate further work. So they do have an inner monologue, which can be observed. There are also systems which summarize what the LLM has been doing and feed the summaries back into the LLM prompts. The idea is to create medium-term memories. When a query comes in, the most important and relevant summaries are fetched and fed…

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

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency — mentioned by gmerc

Fri, 28 Apr 2023 02:06:17 GMT

You were saying? https://arxiv.org/abs/2304.11477

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

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency — HN submission

Thu, 27 Apr 2023 22:34:16 GMT

LLM with Planning

81 points; 16 discussion replies on HN. Paper and source history. A submission is not an endorsement.