跳到正文
Jones Ray

ScholarPulse 日报 2026-09-26

2026-09-26 学术简报:2 篇。该工作提出用仿真在部署前筛选生产级客户体验 AI 代理,并在 Nubank 高流量客服场景中验证其线上收益。

今日速览

序号标题来源日期主题推荐等级
1Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M ScalearXiv2026-09-24RAG高
2KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel OptimizationarXiv2026-09-24AI-Agent高

重点论文与技术动态

1. Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale

一句话结论

该工作提出用仿真在部署前筛选生产级客户体验 AI 代理,并在 Nubank 高流量客服场景中验证其线上收益。

核心内容

方法与数据

价值判断

摘要 Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools reliably. Manual end-to-end testing offers limited coverage, while live experiments expose customers to failures that can erode trust. We present a hypothesis-driven simulation workflow for screening candidate CX agents before deployment. Synthetic customers react to agent responses and simulated tool outputs enable multi-step agentic workflows without invoking production backends. We use the Snowglobe simulator on Nubank's Card Delivery agent and its expanded successor, Card Management - Nubank's highest-volume chat-support agent in Brazil. Across 4 deployed versions, simulated and production version-level binary evaluator scores show high correlation. Simulation-guided iteration increased transactional net promoter score (tNPS) by 36.69 points in a live A/B test. We also screened open-weight configurations in over 16,000 simulated conversations. In a subsequent live A/B test, the selected model increased self-service rate (SSR) by 8.82 percentage points to the highest level observed at Nubank, with no statistically significant change in tNPS. Simulation made broad exploration of models, reasoning settings, and prompts feasible without customer exposure, enabling production improvements that would have been impractical to pursue through live experimentation alone.

2. KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

一句话结论

KernelOPT 把编译后的 PyTorch 模型当作结构化对象,只优化生成的 Triton 子内核,并用四道验证门控保证端到端正确与性能,在 KernelBench 上相对 torch.compile 获得几何平均加速。

核心内容

方法与数据

价值判断

摘要 Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted kernel optimizers can close this gap for standalone kernels, yet treat compiled models as black boxes, generally optimizing individual standalone kernels without respecting the compiler's structural decisions or verifying the model end-to-end. We present KernelOPT, a multi-agent system that treats compiled models as structured artifacts. It preserves vendor library calls (cuBLAS, cuDNN) and exclusively targets generated Triton sub-kernels using five profiling-guided LLM agents. A four-gate verification cascade of static validation, multi-seed correctness, model-level float64-fallback verification, and performance gating filters candidates during optimization and verifies the re-stitched model end-to-end. If no candidate passes all four gates, the system preserves the compiler baseline. The system accepts PyTorch nn.Modules, standalone Triton kernels, and Helion kernels. Evaluated on 250 KernelBench problems, KernelOPT achieves geometric mean speedups over \texttt{torch.compile} of 1.40$\times$ (Level 1: 51/100), 1.15$\times$ (Level 2: 31/100), and 1.07$\times$ (Level 3: 12/50) across all problems.