4). Retrieval-Augmented Reasoning Model Introduces RARE, a new paradigm for training domain-specific LLMs that focuses on reasoning, not memorization.
@dair_ai
-
CodeScientist: AI System Autonomously Generates Tests Scientific Hypotheses
By
–
3). CodeScientist Researchers at AI2 release CodeScientist, a system that autonomously generates and tests scientific hypotheses via code-based experimentation.
-
Cohere Launches Command A: 111B Parameter Enterprise LLM
By
–
2). Command A: An Enterprise-Ready LLM Cohere announced Command A, a 111B parameter open-weights LLM built for enterprise-grade RAG, agents, code, and multilingual tasks.
-
GNNs Predict Agentic Workflow Performance with FLORA-Bench
By
–
10). GNNs as Predictors of Agentic Workflow Performances This work introduces FLORA-Bench, a large-scale benchmark to evaluate GNN-based predictors for automating and optimizing agentic workflows. https://
arxiv.org/abs/2503.11301 -
DeepMesh: Transformer System Generates Artist-Quality 3D Meshes
By
–
8). DeepMesh
— DAIR.AI (@dair_ai) 23 mars 2025
A transformer-based system that generates high-quality 3D meshes with artist-like topology.https://t.co/j1PobdujUG8). DeepMesh A transformer-based system that generates high-quality 3D meshes with artist-like topology.
-
Deep Learning Phenomena Are Not Mysterious or Exclusive
By
–
9). Deep Learning is Not So Mysterious or Different Argues that deep learning phenomena such as benign overfitting, double descent, and the success of overparametrization are neither mysterious nor exclusive to neural networks.
-
Efficient Reasoning Techniques: Optimizing AI Model Performance
By
–
6). A Survey on Efficient Reasoning Investigates techniques to address the "overthinking phenomenon" in reasoning, categorizing existing methods into model-based optimizations, output-based reasoning reductions, and prompt-based efficiency enhancements.
-
Agentic Memory Systems for LLM Agents Long-Term Tasks
By
–
7). Agentic Memory for LLM Agents Proposes a new agentic memory system for LLM agents, addressing the need for long-term memory in complex real-world tasks.
-
Optimal Scaling of Skills in LLMs: Knowledge vs Code
By
–
4). Compute Optimal Scaling of Skills Investigate how different skills (knowledge-based QA vs. code generation) exhibit contrasting optimal scaling behaviors in LLMs.
-
Survey of Reasoning Techniques in Language Models
By
–
5). Thinking Machines This survey provides an overview and comparison of existing reasoning techniques and presents a systematic survey of reasoning-imbued language models.