让AI助手在对话中动态调整工具使用，提升多轮任务规划能力。
Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation
- 用注意力缓存跟踪历史信息，动态选择工具并压缩上下文。
- 多轮任务准确率提升14%，幻觉减少37%，成本远低于GPT-4。
- 无需重训练即可适配新工具，适合医疗、智能家居等动态场景。
检索增强生成（RAG）通过引入外部知识源和工具，显著提升了大语言模型（LLM）的输出质量。然而，现有RAG系统通常仅支持静态、单轮交互，且工具集固定，难以应对医疗、智能家居等动态领域中用户意图、可用工具和上下文随时间变化的需求。本文提出轻量级框架动态上下文调优（DCT），可在不重新训练的前提下支持多轮对话与可变工具环境。DCT结合基于注意力的上下文缓存以追踪相关信息，采用LoRA实现动态域特定工具检索，并通过高效上下文压缩保持输入在LLM上下文长度限制内。在合成及真实世界基准上的实验表明，DCT使计划准确率提升14%，幻觉减少37%，同时达到接近GPT-4的性能，但成本显著更低。此外，DCT可泛化至未见过的工具，支持跨动态环境的可扩展、自适应智能助手。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has significantly advanced large language models (LLMs) by grounding their outputs in external tools and knowledge sources. However, existing RAG systems are typically constrained to static, single-turn interactions with fixed toolsets, making them ill-suited for dynamic domains such as healthcare and smart homes, where user intent, available tools, and contextual factors evolve over time. We present Dynamic Context Tuning (DCT), a lightweight framework that extends RAG to support multi-turn dialogue and evolving tool environments without requiring retraining. DCT integrates an attention-based context cache to track relevant past information, LoRA-based retrieval to dynamically select domain-specific tools, and efficient context compression to maintain inputs within LLM context limits. Experiments on both synthetic and real-world benchmarks show that DCT improves plan accuracy by 14% and reduces hallucinations by 37%, while matching GPT-4 performance at significantly lower cost. Furthermore, DCT generalizes to previously unseen tools, enabling scalable and adaptable AI assistants across a wide range of dynamic environments.
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。