2. MEM1 This work introduces MEM1, an RL framework for training language agents that operate efficiently over long-horizon, multi-turn tasks by learning to consolidate memory and reasoning into a compact internal state.
@dair_ai
-
LlamaRL: Distributed Async RL Framework for Large LLM Training
By
–
9. LLamaRL LlamaRL is a fully-distributed, asynchronous reinforcement learning framework designed for efficient large-scale LLM training (8B to 405B+ models).
-
Google DeepMind AI Platform Predicts Cyclone Tracks 15 Days
By
–
10. Predicting a Cyclone’s Track with AI Google DeepMind's Weather Lab debuts an interactive platform featuring an AI cyclone forecasting model that generates 50 ensemble scenarios up to 15 days ahead, outperforming traditional systems in track and intensity predictions.
-
Mistral Launches Magistral: Reasoning-Focused LLM with Custom RL Stack
By
–
7. Magistral Mistral introduces Magistral, its first reasoning-focused LLM line, alongside a custom RL training stack that enables pure reinforcement learning from scratch.
-
Code Researcher: Deep Bug Resolution Agent for Complex Systems
By
–
8. Code Researcher Code Researcher is a deep research agent designed to resolve complex bugs in large systems’ code by leveraging multi-step reasoning over semantics, patterns, and commit history.
-
ComfyUI-R1: 7B Reasoning Model for Automated Workflow Generation
By
–
6. ComfyUI-R1 Introduces ComfyUI-R1, a 7B-parameter large reasoning model fine-tuned for automatic workflow generation in the ComfyUI ecosystem.
-
Self-Adapting Language Models Through Reinforcement Learning
By
–
5. Self-Adapting Language Models It proposes a novel framework that enables LLMs to adapt themselves through reinforcement learning by generating their own fine-tuning data and update directives, referred to as “self-edits.”
-
Reinforcement Pre-Training: Bridging LLM Pretraining and Reasoning
By
–
3. Reinforcement Pre-Training This paper introduces Reinforcement Pre-Training (RPT), a new paradigm that bridges LLM pretraining and RL by reinterpreting next-token prediction as a reasoning task rewarded via verifiable correctness.
-
Meta AI Introduces V-JEPA 2 for Video Understanding
By
–
2. V-JEPA 2 Meta AI introduces V-JEPA 2, a scalable joint-embedding predictive architecture for self-supervised video learning, targeting the goal of building a generalist world model capable of understanding, predicting, and planning in the physical world.
-
Text-to-LoRA: Generate Adapters from Natural Language
By
–
1. Text-to-LoRA Introduces a hypernetwork-based approach for instantly generating LoRA adapters from natural language task descriptions, removing the need for conventional task-specific fine-tuning.