解决对话系统响应快与任务复杂间的矛盾，支持实时互动与后台智能执行并行。
DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
- 将实时回复与异步任务解耦，通过共享状态同步结果。
- 上线后7日留存率提升至34.2%，复杂任务完成率达65.2%。
- 适合需要高交互性与强智能的工业级对话系统部署。
生产环境中的沉浸式对话系统始终面临响应速度与长程任务能力之间的权衡。轻量级对话可实现实时交互，但涉及规划与工具调用（如搜索、媒体生成）的任务会产生长尾延迟，损害轮次衔接、角色一致性与用户信任。为此，我们提出 DuCCAE（Conversation while Collaboration with Augmentation and Evolution），一个部署于百度搜索的混合对话引擎，服务数百万用户。DuCCAE 将实时响应生成与异步代理执行解耦，并通过共享状态（包含会话上下文与执行轨迹）进行同步，使异步结果可无缝回流至对话中。系统协调五个子模块——Info、Conversation、Collaboration、Augmentation、Evolution——支持多代理协作与持续进化。我们通过离线基准测试（Du-Interact 数据集）与百度搜索的大规模生产评估综合验证了 DuCCAE。实验表明，其在代理执行可靠性与对话质量上优于强基线，同时将延迟控制在严格实时预算内。关键的是，自2025年6月部署以来，真实数据证实其显著有效性：7日留存率翻三倍至34.2%，复杂任务完成率飙升至65.2%。该混合架构成功在保持对话连续性的同时实现可靠的代理执行，为工业级可扩展代理系统的落地提供了实用指南。
原文摘要 · Abstract (English)
Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightweight turns, but requests involving planning and tool invocation (e.g., search and media generation) produce heavy-tail execution latency that degrades turn-taking, persona consistency, and user trust. To address this challenge, we propose DuCCAE (Conversation while Collaboration with Augmentation and Evolution), a hybrid engine for immersive conversation deployed within Baidu Search, serving millions of users. DuCCAE decouples real-time response generation from asynchronous agentic execution and synchronizes them via a shared state that maintains session context and execution traces, enabling asynchronous results to be integrated back into the ongoing dialogue. The system orchestrates five subsystems-Info, Conversation, Collaboration, Augmentation, and Evolution-to support multi-agent collaboration and continuous improvement. We evaluate DuCCAE through a comprehensive framework that combines offline benchmarking on the Du-Interact dataset and large-scale production evaluation within Baidu Search. Experimental results demonstrate that DuCCAE outperforms strong baselines in agentic execution reliability and dialogue quality while reducing latency to fit strict real-time budgets. Crucially, deployment metrics since June 2025 confirm substantial real-world effectiveness, evidenced by a tripling of Day-7 user retention to 34.2% and a surge in the complex task completion rate to 65.2%. Our hybrid architecture successfully preserves conversational continuity while enabling reliable agentic execution, offering practical guidelines for deploying scalable agentic systems in industrial settings.
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。