Merge branch 'main' of github.com:microsoft/Trace into main

README.md

@@ -1,8 +1,10 @@
 # Trace: End-to-end Generative Optimization for AI Systems and Agents
 
 
-![Static Badge](https://img.shields.io/badge/Build-pass-green)
-![Static Badge](https://img.shields.io/badge/Version-v0.1.0-blue)
+![PyPI](https://img.shields.io/pypi/v/trace-opt)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/trace-opt)
+![GitHub license](https://img.shields.io/badge/License-MIT-blue.svg)
+[![arXiv](https://img.shields.io/badge/arXiv-1234.56789-b31b1b.svg)](https://arxiv.org/abs/2406.16218)
 
 Trace is a new AutoDiff-like tool for training AI systems end-to-end with general feedback (like numerical rewards or losses, natural language text, compiler errors, etc.). Trace generalizes the back-propagation algorithm by capturing and propagating an AI system's execution trace. Trace is implemented as a PyTorch-like Python library. Users write Python code directly and can use Trace primitives to optimize certain parts, just like training neural networks!
 
@@ -20,7 +22,8 @@ Or for development, clone the repo and run the following.
 
     pip install -e .
 
-The library requires Python >= 3.8. The installation script will git clone [AutoGen](https://github.com/microsoft/autogen). You may require [Git Large File Storage](https://git-lfs.com/) if git is unable to clone the repository otherwise.
+The library requires Python >= 3.9. The installation script will git clone [AutoGen](https://github.com/microsoft/autogen). You may require [Git Large File Storage](https://git-lfs.com/) if git is unable to clone the repository otherwise.
+
 
 ## Citation
 If you use this code in your research please cite the following [publication](https://arxiv.org/abs/2406.16218):
@@ -32,6 +35,13 @@ If you use this code in your research please cite the following [publication](ht
   year={2024}
 }
 ```
+## Updates
+
+ - **2024.10.21**    New [paper](https://arxiv.org/abs/2410.15625) by Nvidia, Stanford, Visa, & Intel applies Trace to optimize for mapper code of parallel programming. Trace (OptoPrime) learns code achieving 1.3X speed up under 10 minutes, compared with the code optimized by domain expert.
+ - **2024.9.25** [Trace Paper](https://arxiv.org/abs/2406.16218) is accepted to NeurIPS 2024.
+ - **2024.9.14** TextGrad is available as a Trace optimizer.
+
+
 
 ## Evaluation
 A previous version of Trace was tested with gpt-4-0125-preview on numerical optimization, simulated traffic control, big-bench-hard, and llf-metaworld tasks, which demonstrated good optimization performance on multiple random seeds; please see the paper for details.