MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
"多轮推理" 相关文章
首个多轮LLM Router问世, Router-R1可让大模型学会「思考–路由–聚合」
TriMediQ: A Triplet-Structured Approach for Interactive Medical Question Answering
Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
超越样本级RL！人大×快手提出ARPO：熵驱动Agent探索，多轮推理性能飙升
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
三思而后行，让大模型推理更强的秘密是「THINK TWICE」？
