跳到正文
Jones Ray

ScholarPulse 日报 2026-09-27

2026-09-27 学术简报:2 篇。KREX 是共享 GPU 的并发内核基准测试运行时,以区域级独占保真、区域外并发,提升智能体测试吞吐。

今日速览

序号标题来源日期主题推荐等级
1KREX: Concurrent Kernel Benchmarking on Shared GPUs via Region-Granular ExclusivityarXiv2026-09-24AI-Agent高
2How does Adversarial Influence Scale in Multi-Agent Systems?arXiv2026-09-24AI-Agent高

重点论文与技术动态

1. KREX: Concurrent Kernel Benchmarking on Shared GPUs via Region-Granular Exclusivity

一句话结论

KREX 是共享 GPU 的并发内核基准测试运行时,以区域级独占保真、区域外并发,提升智能体测试吞吐。

核心内容

方法与数据

价值判断

摘要 LLM agents automate GPU kernel optimization by repeatedly composing candidates and measuring their duration on real GPUs. Existing systems preserve measurement fidelity by reserving a GPU for an entire agent session or benchmarking command. However, this results in poor utilization because only a small fraction of command execution requires exclusive GPU access. Sharing GPUs could recover this idle capacity, but introduces contention that compromises measurement fidelity and misdirects the agent's search. We present KREX, a runtime for concurrent kernel agent benchmarking with region-granular exclusivity. KREX lets agents mark critical regions involving timing-sensitive operations within a benchmarking command. The runtime then enforces exclusivity within marked regions and allows concurrent execution outside them, achieving high throughput while preserving measurement fidelity. To enforce in-region exclusivity, KREX blocks new competing GPU submissions and drains outstanding work before freezing sibling processes and isolating CPU cores, protecting both GPU execution and the host threads that drive measurements. To maximize off-region concurrency, KREX reuses GPU contexts in persistent context processes to avoid repeated, node-wide serialized context creation. We evaluate KREX on NVIDIA and AMD GPUs. Compared with command-granular exclusivity baselines, KREX delivers up to $3.4\times$ the benchmarking throughput with a negligible p95 timing inflation of $0.30\%$, $1.58\%$, and $3.90\%$ for kernels longer than 10 ms, 1 ms, and 0.1 ms, respectively.

2. How does Adversarial Influence Scale in Multi-Agent Systems?

一句话结论

多智能体系统中,抗欺骗能力取决于欺骗者比例而非智能体总数;增加智能体数量不足以防御,因为对手可随群体扩展。

核心内容

方法与数据

价值判断

摘要 Multi-agent deliberation can improve performance, but what happens when some agents do not act in good faith? In practice, an agent may be deceptive and work to subvert the group, whether through its own objectives or external instruction. We study how susceptibility to deception scales as groups increase in size and deceivers become more prevalent. It is not the number of agents in the group that matters, but the proportion of deceivers. We observe that the defection rate, how often initially correct agents switch to an incorrect final answer, rises linearly with this proportion. Whereas humans in comparable conformity studies are reliably swayed only when misleading confederates form a majority, LLM agents defect regularly even when deceivers remain a minority. Susceptibility also depends on which models are interacting, especially on the honest agent side. Unexpectedly, allowing deceivers to coordinate privately can make them less effective. Altogether, our results show that adding more agents is therefore not a sufficient defense, because the adversary can simply scale with the group.