facebookresearch / MLGym
MLGym A New Framework and Benchmark for Advancing AI Research Agents
☆459Updated this week
Alternatives and similar repositories for MLGym:
Users that are interested in MLGym are comparing it to the libraries listed below
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym☆403Updated 2 weeks ago
- Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆477Updated 2 weeks ago
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆656Updated 2 months ago
- ☆493Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆311Updated 3 months ago
- Recipes to scale inference-time compute of open models☆1,048Updated last month
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…☆283Updated last week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆300Updated 4 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆725Updated this week
- procedural reasoning datasets☆541Updated this week
- System 2 Reasoning Link Collection☆812Updated 2 weeks ago
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle☆244Updated this week
- Search-o1: Agentic Search-Enhanced Large Reasoning Models☆748Updated 3 weeks ago
- AWM: Agent Workflow Memory☆252Updated last month
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆140Updated this week
- ☆1,011Updated 3 months ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆334Updated last month
- 🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.☆283Updated last week
- Verifiers for LLM Reinforcement Learning☆727Updated last week
- Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi e…☆428Updated 2 weeks ago
- An agent benchmark with tasks in a simulated software company.☆273Updated last week
- ☆574Updated 2 weeks ago
- Pretraining code for a large-scale depth-recurrent language model☆709Updated 2 weeks ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,015Updated 2 months ago
- LIMO: Less is More for Reasoning☆875Updated last month
- ☆913Updated 2 months ago
- ☆262Updated 2 weeks ago
- A curated collection of LLM reasoning and planning resources, including key papers, limitations, benchmarks, and additional learning mate…☆249Updated last month
- Automatic evals for LLMs☆346Updated this week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆168Updated 2 months ago