2026
R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
ICLR 2026poster
Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL) to autonomously generate…