nex-agi/DeepSeek-V3.1-Nex-N1
671B
•
Updated
•
84
•
25
AGI, Nex
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping