simpletir-multi-turn-tool-reasoning-rl

【开发与工程】Train LLMs for multi-turn tool-integrated reasoning end-to-end using RL without supervised pretraining. SimpleTIR stabilizes training by filtering void turns (responses lacking code blocks or final answers) to prevent gradient explosion from distributional drift, enabling discovery of emergent reasoning patterns like self-correction and cross-validat…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准