agent/papers/items/2026-2603-08721-kernelcraft-benchmarking-for-agentic-close-to-metal-kernel-generation-on-emergin.md

Paper: KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware

---

type: paper title: "KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware" authors: Jiayi Nie, Haoran Wu, Yao Lai, Zeyu Cao, Cheng Zhang, Binglei Lou, Erwei Wang, Jianyi Cheng, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2603.08721 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-02-10 updated_at: 2026-05-29 status: queued relevance: high topics:

• agent-evaluation
• reasoning
• workflow-agent methods:

benchmarks:

models:

datasets:

• cs.AR
• cs.LG
• cs.SE related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 17 collection_queries: function-calling

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: function-calling
• inferred topics: agent-evaluation, reasoning, workflow-agent
• arXiv categories: cs.AR, cs.LG, cs.SE
• collection score: 17

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2603.08721