facebookresearch / RAMLinks
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
☆344Updated last month
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☆260Updated 9 months ago
- Tina: Tiny Reasoning Models via LoRA☆316Updated 4 months ago
- [ICLR 2026] Learning to Reason without External Rewards☆389Updated last week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆371Updated last year
- Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike stat…☆418Updated 2 weeks ago
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆405Updated 2 months ago
- ☆112Updated last year
- ☆328Updated 8 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆216Updated 2 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆468Updated 8 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆623Updated last week
- Async pipelined version of Verl☆124Updated 9 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆178Updated 6 months ago
- LOFT: A 1 Million+ Token Long-Context Benchmark☆225Updated 7 months ago
- [Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆177Updated 3 weeks ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 6 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆68Updated 9 months ago
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆191Updated 7 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆227Updated 3 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆277Updated 3 months ago
- A Gym for Agentic LLMs☆439Updated 2 weeks ago
- "Improving Mathematical Reasoning with Process Supervision" by OPENAI☆114Updated last week
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆260Updated 8 months ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆138Updated last month
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆167Updated 3 months ago
- ☆352Updated 6 months ago
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"☆316Updated 2 years ago
- ☆203Updated 9 months ago
- Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆273Updated 3 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆245Updated last year