作者位次 #3/8ACL 2026Poster· Natural Language Processing
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
Yifeng Ding · Hung Le · Songyang Han · Kangrui Ruan · Zhenghui Jin · Varun Kumar · Zijian Wang · Anoop Deoras
摘要
Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) – where models iteratively reason, generate code, and verify through execution – remains challenging for existing reinforcement learning (RL) approaches. Current RL methods, exemplified by Group Relative Policy O...