用多轮生成构建可解释的智能体推理系统，解决大模型幻觉与失控问题。
Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
- 通过多轮生成模拟智能体行为，每步输出带证据的中间结果
- 引入步骤索引构建图结构，提升复杂逻辑推理能力
- 在6个基准上显著优于现有方法，适合复杂任务求解
思维链提示显著提升了大语言模型的推理能力，但仍存在幻觉、可解释性差和生成不可控三大问题。为此，我们提出AgentCOT——一种基于大模型的自主智能体框架，通过多轮大模型生成以智能体风格解决复杂任务。每一步中，AgentCOT选择动作并执行，生成带有支持证据的中间结果。此外，将步骤索引融入推理过程，构建用于复杂推理逻辑的图结构。我们引入两种新策略以增强AgentCOT性能。在六个常见基准上的大量实验验证了该方法的有效性，结果表明其显著优于当前主流方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。