Attentive Reasoning Queries：一种优化大型语言模型指令遵循的系统化方法
Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models
AI总结：
本文提出结构化推理方法 ARQs，通过领域专属推理蓝图和针对性查询引导 LLMs 系统化执行推理步骤，有效解决了多轮对话中复杂指令遵循的难题，并在 87 个场景中取得 90.2% 的成功率，显著优于基线方法。
摘要：
我们提出了 Attentive Reasoning Queries (ARQs)，这是一种新颖的结构化推理方法，通过领域专属的推理蓝图显著提升了大型语言模型的指令遵循能力。尽管 LLMs 在各类任务中展现出卓越能力，但在多轮对话中往往无法持续遵守复杂的、特定用例的指令，这给关键业务应用带来了挑战。ARQs 通过引导 LLMs 执行系统化推理步骤来解决这一局限，这些步骤采用针对性查询来重申关键指令，并在整个完成过程中促进中间推理。在 Parlant（我们面向客户的可靠智能体框架，ARQs 正是因实际需求而诞生于其中）的广泛测试中，ARQs 在 87 个测试场景中达到了 90.2% 的成功率，优于 Chain-of-Thought 推理 (86.1%) 和直接响应生成 (81.5%)。ARQs 在解决指南重新应用和幻觉预防等持续性失败模式方面表现出显著优势。分析还表明，经过精心设计，ARQs 在计算效率上有潜力超越自由形式的推理。这些发现表明，结构化推理方法为控制 LLMs 在复杂场景中处理信息和做出决策提供了有效机制。
英文摘要：
We present Attentive Reasoning Queries (ARQs), a novel structured reasoning approach that significantly improves instruction-following in Large Language Models through domain-specialized reasoning blueprints. While LLMs demonstrate remarkable capabilities across diverse tasks, they often fail to maintain adherence to complex, use-case-specific instructions during multi-turn conversations, presenting challenges for business-critical applications. ARQs address this limitation by guiding LLMs through systematic reasoning steps with targeted queries that reinstate critical instructions and facilitate intermediate reasoning throughout the completion process. In extensive testing within Parlant, our framework for reliable customer-facing agents in which ARQs were born out of necessity, they achieved a 90.2% success rate across 87 test scenarios, outperforming both Chain-of-Thought reasoning (86.1%) and direct response generation (81.5%). ARQs showed particular strength in addressing persistent failure modes like guideline re-application and hallucination prevention. Our analysis also revealed that ARQs can potentially be more computationally efficient than free-form reasoning when carefully designed. These findings demonstrate that structured reasoning approaches provide effective mechanisms for controlling how LLMs process information and make decisions in complex scenarios.
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。
