arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.12411cs.CL
收藏

多轮大语言模型生成的复杂任务文本化智能体风格推理

Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation

Beijing Jiaotong University(北京交通大学);Baidu Inc(百度公司);University of Science and Technology of China(中国科学技术大学);Beijing Normal University(北京师范大学)

Chen Liang, Zhifan Feng, Zihe Liu, Wenbin Jiang, Jinan Xu, Yufeng Chen, Yong Wang

AI总结:

针对思维链推理的幻觉、可解释性差和生成不可控问题,提出基于大语言模型的智能体框架AgentCOT,通过多轮生成、动作执行和图结构推理,在六个基准上显著提升性能。

摘要:

思维链提示显著提升了大型语言模型的推理能力,但仍面临三个问题:幻觉问题、可解释性受限以及生成过程不可控。为应对这些挑战,我们提出了AgentCOT,一个基于大语言模型的自主智能体框架,能够通过多轮大语言模型生成以智能体风格解决复杂问题。在每一步中,AgentCOT选择一个动作并执行该动作,以生成带有支持证据的中间结果。此外,我们将步骤索引整合到推理过程中,形成用于复杂推理逻辑的图结构。我们引入了两种新策略来增强AgentCOT的性能。我们在六个常见基准上进行了大量实验,以验证我们方法的有效性。结果表明,我们的方法相较于当前有竞争力的方法带来了显著的改进。

英文摘要:

Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we present AgentCOT, a llm-based autonomous agent framework, which can solve complex problems in an agent-style manner by multiple round LLM generation. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. In addition, we integrate the step's index into the reasoning process to form a graph structure for complex inference logic. We introduce two new strategies to enhance the performance of AgentCOT.We conduct extensive experiments to verify the effectiveness of our method on six common benchmarks. Results exhibit that our method brings in substantial improvements over current competitive approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑