arXiv cs.AI· Youwei Bao, Chengpeng Wang, Simin Chen·· 13 小时前AI 评分34
论文提出在智能体内核生成中强制实施批次不变性
God Does Not Play Dice: Enforcing Batch Invariance in Agentic Kernel Generation
AI 导读
针对 LLM 服务动态批处理导致同一请求输出不可复现的问题，研究者在 83 个可批处理已发布产物中确认了 19 例批次不变性（BI）违规。为此提出一种结合契约引导静态依赖分析与跨批次上下文按位一致性动态验证的工具，作为通用内核智能体的插件，将 BI 通过率从 67.6% 提升至 91.9%，同时保留基线几何平均加速比的 91.8%。
正文 · 原文
Abstract:Large language model (LLM) serving systems dynamically batch user requests for GPU execution, so the same request may be processed alongside different requests across runs. If the GPU kernels lack batch invariance (BI), this changing batch context can alter the numerical output for an unchanged input, undermining reproducibility. Existing kernel generation agents focus on correctness and efficiency but \emph{overlook BI}. We find 19 confirmed BI violations among 83 batch-applicable released artifacts. To address this limitation, we propose \tool, which combines contract-guided static dependency analysis with dynamic validation of bitwise consistency across batch contexts. \tool is designed as a plug-in component for general kernel agents, allowing their original optimization capabilities to be reused while adding BI enforcement. We integrate it as successive acceptance gates in the optimization loop, rejecting structurally risky or dynamically non-invariant candidates before performance benchmarking and returning feedback to the agent. Experiments across three agent frameworks under baseline and BI-aware generation on real world LLM serving tasks show that \tool improves the BI pass rate from 67.6\% to 91.9\% while retaining 91.8\% of the baseline geometric mean speedup. These results demonstrate that \tool can be incorporated into kernel optimization by agents as an additional reliability objective alongside correctness and speed.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.36623 [cs.AI] |
| (or arXiv:2610.36623v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36623 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Simin Chen [view email]
[v1]
Tue, 27 Oct 2026 04:27:11 UTC (13,091 KB)
来源：arXiv cs.AI · arxiv.org