facebookresearch / RAMLinks
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
☆312Updated last week
Alternatives and similar repositories for RAM
Users that are interested in RAM are comparing it to the libraries listed below
Sorting:
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆254Updated 7 months ago
- Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike stat…☆391Updated 3 weeks ago
- Tina: Tiny Reasoning Models via LoRA☆309Updated 2 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆67Updated 8 months ago
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆383Updated 2 weeks ago
- ☆226Updated 9 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆209Updated 2 weeks ago
- ☆109Updated last year
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆359Updated last year
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆179Updated 5 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆224Updated last month
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆460Updated 6 months ago
- Code for the paper: "Learning to Reason without External Rewards"☆380Updated 5 months ago
- ☆328Updated 6 months ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆134Updated 3 months ago
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆161Updated last month
- Async pipelined version of Verl☆125Updated 8 months ago
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆187Updated 5 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆275Updated last month
- ☆104Updated 2 months ago
- ☆344Updated 4 months ago
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆279Updated 2 months ago
- ☆92Updated 6 months ago
- AIRA-dojo: a framework for developing and evaluating AI research agents☆116Updated 3 weeks ago
- ☆125Updated 9 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆181Updated 4 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆349Updated 7 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training☆312Updated 7 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆112Updated 10 months ago