π The First Self-Improving agents with RL / Prompting Optimization
Python agentaigptmulti-agentpythonreinforcement-learningself-improvementsociety-of-mindswarm-intelligence
Fix links to the new repo (#10)
Dmitrii Khizbullinc8a997013e82
diff --git a/README.md b/README.mdindex 05c994a..e0bde01 100644--- a/README.md+++ b/README.md@@ -1,6 +1,6 @@[](https://gptswarm.org)[](https://arxiv.org/abs/2402.16823)-[](https://github.com/mczhuge/GPTSwarm/blob/main/LICENSE)+[](https://github.com/metauto-ai/GPTSwarm/blob/main/LICENSE)[](https://github.com/metauto-ai/gptswarm/issues)[](https://twitter.com/AI_KAUST)[](https://metauto.ai/images/wechat.jpeg)@@ -85,16 +85,16 @@ inputs = {"task": task, "files": files}danswer = swarm.run(inputs)```-Check out the minimal Swarm example in Colab here: [](https://colab.research.google.com/github/mczhuge/GPTSwarm/blob/main/notebooks/demo_swarm.ipynb).+Check out the minimal Swarm example in Colab here: [](https://colab.research.google.com/github/metauto-ai/GPTSwarm/blob/main/notebooks/demo_swarm.ipynb).-See how to create a custom Agent and run a Swarm with it here: [](https://colab.research.google.com/github/mczhuge/GPTSwarm/blob/main/notebooks/demo_custom_agent.ipynb).+See how to create a custom Agent and run a Swarm with it here: [](https://colab.research.google.com/github/metauto-ai/GPTSwarm/blob/main/notebooks/demo_custom_agent.ipynb).Here is a Youtube video on how to run the demo notebooks:[<img src="assets/youtube_preview.png" width="75%">](https://www.youtube.com/watch?v=QOLQse5ZBV8&t=8s&ab_channel=GPTSwarm "Running swarm inference")-**π See [our experiments](https://github.com/mczhuge/GPTSwarm/tree/main/experiments) for more advanced use of our framework.**+**π See [our experiments](https://github.com/metauto-ai/GPTSwarm/tree/main/experiments) for more advanced use of our framework.**## Class diagramdiff --git a/experiments/README.md b/experiments/README.mdindex 1abeba4..8e49987 100644--- a/experiments/README.md+++ b/experiments/README.md@@ -1,29 +1,5 @@## Run the following commands to reproduce our experiments in the paper-### Download dataset--The datasets are stored in git LFS. If git LFS is already installed in your system, no action is required. To check if git LFS is installed, run:-```bash-git lfs-```-If you see an error message, install git LFS via this instruction](https://docs.github.com/en/repositories/working-with-files/managing-large-files/installing-git-large-file-storage). Then run:-```bash-git lfs install-git lfs pull-```--### Include necessary submodules--If the project has already been cloned:-```bash-git submodule init-git submodule update-```-or a one-liner:-```bash-git submodule update --init --recursive-```-### **MMLU**Run the baseline:```bashdiff --git a/pyproject.toml b/pyproject.tomlindex 2269552..fbed478 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -26,8 +26,8 @@ dependencies = {file = ["requirements_py310_macos.txt"]}dev = ["black", "bumpver", "isort", "pip-tools", "pytest"][project.urls]-Homepage = "https://github.com/mczhuge/GPTSwarm"-Issues = "https://github.com/mczhuge/GPTSwarm/issues"+Homepage = "https://github.com/metauto-ai/GPTSwarm"+Issues = "https://github.com/metauto-ai/GPTSwarm/issues"[build-system]requires = ["setuptools>=61.0.0", "wheel"]diff --git a/swarm/environment/agents/gaia/normal_io.py b/swarm/environment/agents/gaia/normal_io.pyindex 693ec3e..c1f446d 100644--- a/swarm/environment/agents/gaia/normal_io.py+++ b/swarm/environment/agents/gaia/normal_io.py@@ -1,10 +1,5 @@#!/usr/bin/env python# -*- coding: utf-8 -*--"""-Author : wenyi-Review :-File : node.py-"""from swarm.graph import Graphfrom swarm.environment.operations import DirectAnswerdiff --git a/swarm/environment/tools/coding/README.md b/swarm/environment/tools/coding/README.mdindex 22debb9..72d2f90 100644--- a/swarm/environment/tools/coding/README.md+++ b/swarm/environment/tools/coding/README.md@@ -1 +1 @@-[executor_types.py](https://github.com/mczhuge/GPTSwarm/blob/main/swarm/environment/tools/coding/executor_types.py), [executor_utils.py](https://github.com/mczhuge/GPTSwarm/blob/main/swarm/environment/tools/coding/executor_utils.py) and [python_executor.py](https://github.com/mczhuge/GPTSwarm/blob/main/swarm/environment/tools/coding/python_executor.py) under this directory are directly adopted from the [Reflexion project](https://github.com/noahshinn/reflexion/tree/main/programming_runs/executors).+[executor_types.py](https://github.com/metauto-ai/GPTSwarm/blob/main/swarm/environment/tools/coding/executor_types.py), [executor_utils.py](https://github.com/metauto-ai/GPTSwarm/blob/main/swarm/environment/tools/coding/executor_utils.py) and [python_executor.py](https://github.com/metauto-ai/GPTSwarm/blob/main/swarm/environment/tools/coding/python_executor.py) under this directory are directly adopted from the [Reflexion project](https://github.com/noahshinn/reflexion/tree/main/programming_runs/executors).diff --git a/swarm/llm/price.py b/swarm/llm/price.pyindex 7e25b5c..0ddaacd 100644--- a/swarm/llm/price.py+++ b/swarm/llm/price.py@@ -1,10 +1,5 @@#!/usr/bin/env python# -*- coding: utf-8 -*--"""-Author: mczhuge-Review :-File: price.py-"""from swarm.utils.log import swarmlogfrom swarm.utils.globals import Cost