作者位次 #3/7ACL 2026Poster· Natural Language Processing
Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees
Kun Li · Zenan Xu · Junan Li · Zengrui Jin · Jinghao Deng · Zexuan Qiu · Bo Zhou
摘要
Tool-Integrated Reasoning has emerged as a key paradigm to augment Large Language Models (LLMs) with computational capabilities, yet integrating tool-use into long Chain-of-Thought (long CoT) remains underexplored, largely due to the scarcity of training data and the challenge of integrating tool...