facebookresearch / MLGym
MLGym A New Framework and Benchmark for Advancing AI Research Agents
☆484Updated 2 weeks ago
Alternatives and similar repositories for MLGym:
Users that are interested in MLGym are comparing it to the libraries listed below
- ☆519Updated last week
- Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆509Updated last month
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym☆438Updated 3 weeks ago
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆685Updated last week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆320Updated 4 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆419Updated 2 weeks ago
- Recipes to scale inference-time compute of open models☆1,058Updated 2 months ago
- Verifiers for LLM Reinforcement Learning☆827Updated 3 weeks ago
- procedural reasoning datasets☆571Updated this week
- Pretraining code for a large-scale depth-recurrent language model☆745Updated last week
- Training Large Language Model to Reason in a Continuous Latent Space☆1,076Updated 3 months ago
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle☆257Updated this week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆304Updated 5 months ago
- System 2 Reasoning Link Collection☆826Updated last month
- ☆1,017Updated 4 months ago
- Automatic evals for LLMs☆373Updated this week
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆139Updated this week
- Understanding R1-Zero-Like Training: A Critical Perspective☆882Updated last week
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…☆305Updated this week
- ☆647Updated 3 weeks ago
- RewardBench: the first evaluation tool for reward models.☆555Updated last month
- ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning☆714Updated this week
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆182Updated last week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.☆331Updated this week
- A bibliography and survey of the papers surrounding o1☆1,187Updated 5 months ago
- LIMO: Less is More for Reasoning☆920Updated 2 weeks ago
- AWM: Agent Workflow Memory☆262Updated 2 months ago
- PyTorch building blocks for the OLMo ecosystem☆197Updated this week
- Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi e…☆449Updated last month
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆171Updated 3 months ago