ConCise: 免训练结论链状态压缩用于经济高效的多步RAG服务
ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services
AI总结：
针对多步RAG中累积输入令牌呈O(N²)增长导致成本高的问题，提出免训练状态层协议ConCise，通过结构化结论链将增长压缩至O(N)，并引入融合生成机制减少API调用，平均节省64.63%令牌且保持可接受精度。
摘要：
多步检索增强生成（RAG）已被广泛部署为基于LLM的Web服务，用于复杂问答，其中迭代检索-推理轮次实现了强大的多跳准确性。然而，这种范式导致历史文档和推理轨迹在各轮次间累积，使累积输入令牌大致呈$O(N^2)$增长，且噪声密度逐渐增加。在基于API的服务架构中，这种增长直接放大了每请求的计费成本、网络负载和响应延迟。现有的压缩方法依赖于预训练模块或GPU级KV缓存访问，引入了与API原生、无服务器和边缘端部署不兼容的模型托管开销。为解决此问题，本文提出ConCise，一种免训练的状态层协议，用于重构多步RAG服务的跨轮次上下文传输。具体来说，ConCise用仅追加的结构化结论链替代原始文本累积，将累积上下文增长从$O(N^2)$压缩至约$O(N)$。此外，引入融合生成机制，在单个API调用中联合发出推理和结论，消除了串行双调用开销带来的重复输入计费。跨三个模型、两个数据集和两个代表性框架的十二个配对配置的广泛实验表明，ConCise实现了平均64.63%的令牌节省，同时保持可接受的准确性，为经济高效的多步RAG服务优化提供了即插即用、易于部署的解决方案。
英文摘要：
Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative retrieval-reasoning rounds deliver strong multi-hop accuracy. However, this paradigm causes historical documents and reasoning traces to accumulate across rounds, inflating cumulative input tokens approximately as $O(N^2)$ with progressively increasing noise density. In API-based service architectures, such growth directly amplifies per-request billing cost, network payload, and response latency. Existing compression approaches rely on pretrained modules or GPU-level KV cache access, introducing model hosting overhead incompatible with API-native, Serverless, and edge-side deployments. To address this issue, this paper proposes ConCise, a training-free state-layer protocol that restructures cross-round context transmission for multi-step RAG services. Specifically, ConCise replaces raw-text accumulation with an append-only chain of structured conclusions, compressing cumulative context growth from $O(N^2)$ to approximately $O(N)$. Furthermore, a fused generation mechanism is introduced to jointly emit reasoning and conclusions in a single API call, eliminating repeated input billing from serial dual-invocation overhead. Extensive experiments across twelve paired configurations spanning three models, two datasets, and two representative frameworks demonstrate that ConCise achieves 64.63\% average token savings while maintaining acceptable accuracy, providing a plug-and-play, deployment-friendly solution for cost-efficient multi-step RAG service optimization.
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。
