ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models · HackerPapers discussions

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models — HN submission

Tue, 27 Feb 2024 13:06:51 GMT

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented LMs (2023)

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models — mentioned by hobofan

Tue, 21 Nov 2023 14:15:51 GMT

Yes, I think that is the general trend. Have one model tuned for reasoning that decides a plan, based on which you invoke other models as tools (see e.g. the ReWOO paper[0]). If I had to guess, an approach like this is what powers the recent Custom GPT/Assistant API products (based on the lag between tool invocations I would guess that they also re-prompt for plan adjustments between every set of tool calls). Do that with a small model and hot-swap LORAs, and it should be possible to build a quite powerful local assistant on consumer hardware. [0]: https://arxiv.org/abs/2305.18323

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

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models — mentioned by kytazo

Fri, 09 Jun 2023 09:50:28 GMT

Papper: https://arxiv.org/abs/2305.18323 Tweet: https://twitter.com/billxbf/status/1663713374910251009?s=20 Code: https://github.com/billxbf/ReWOO

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

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models — HN submission

Fri, 09 Jun 2023 09:47:17 GMT

Decoupling Reasoning from Observations for Efficient Augmented Language Models

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models — mentioned by kordlessagain

Mon, 05 Jun 2023 15:20:17 GMT

It's maybe interesting to think about a simple chat history over time giving some of the knowledge needed for improved interactions as related to the more complex patterns outlined here. Here's a similar paper I ran across this morning: https://arxiv.org/abs/2305.18323. Github is here: https://github.com/billxbf/ReWOO I indexed both documents with my own project, which uses semantic graphs to help with prompt assembly: https://github.com/FeatureBaseDB/DoctorGPT. DoctorGPT doesn't have dynamic prompt chaining yet, but I'm working on it. I hesitate posting any of the analysis of these papers…

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