AI RESEARCH
SAGE-32B: Agentic Reasoning via Iterative Distillation
arXiv CS.AI
•
ArXi:2601.04237v2 Announce Type: replace We nstrate SAGE-32B, a 32B parameters language model that focuses on agentic reasoning and long range planning tasks. Unlike chat models that aim for general conversation fluency, SAGE-32B is designed to operate in an agentic loop, emphasizing task decomposition, tool usage, and error recovery. The model is initialized from the Qwen2.5-32B pretrained model and fine tuned using Iterative Distillation, a two stage