Sweet Rl
Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
AI Agent PlatformOpen Source AI & Machine LearningOpen Source
About
SWEET-RL provides a framework for training large language model (LLM) agents to engage in multi-turn interactions for real-world tasks. It introduces a new benchmark, ColBench, which allows LLM agents to collaborate with human partners on backend programming and frontend design tasks. The implementation focuses on optimizing the training process through a novel reinforcement learning algorithm that enhances performance in collaborative content creation.
Open Source Health
- Stars
- 271
- Forks
- 12
- License
- Not stated
- Last commit
- 1 years ago
Python
Alternatives to Sweet Rl
- RPG_KDD2025by FacebookresearchThis repository provides the code for implementing RPG described in our KDD'25 paper "Generating Long Semantic IDs in Parallel for Recommendation".
- Daggerby Daggerthe missing software stack for CI
- Seamless Communicationby FacebookresearchFoundational Models for State-of-the-Art Speech and Text Translation
- OrienterNetby FacebookresearchSource Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"
- Matrixby FacebookresearchMatrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.
Resources & Links
Related Categories
Using Sweet Rl?
Track its cost next to the rest of your stack and get a reminder before it renews.
Add to my stackVendor
Facebookresearch
Publisher of Fairseq
