MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?

• URL: http://arxiv.org/abs/2603.11935v2
• Date: Sun, 15 Mar 2026 08:45:48 GMT
• Title: MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?
• Abstract summary: Large language models (LLMs) have demonstrated remarkable capabilities in code generation, yet their potential for generating kernels specifically for mobile devices remains largely unexplored.<n>We propose the Mobile Kernel Agent (MoKA), a multi-agent system equipped with repository-aware reasoning and a plan-and-execute paradigm.<n>MoKA achieves state-of-the-art performance, boosting compilation success to 93.7% and enabling 27.4% of generated kernels to deliver measurable speedups over native libraries.
• Score: 15.361816481675325
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in code generation, yet their potential for generating kernels specifically for mobile devices remains largely unexplored. In this work, we extend the scope of automated kernel generation to the mobile domain to investigate the central question: Can LLMs write efficient kernels for mobile devices? To enable systematic investigation, we introduce MobileKernelBench, a comprehensive evaluation framework comprising a benchmark prioritizing operator diversity and cross-framework interoperability, coupled with an automated pipeline that bridges the host-device gap for on-device verification. Leveraging this framework, we conduct extensive evaluation on the CPU backend of Mobile Neural Network (MNN), revealing that current LLMs struggle with the engineering complexity and data scarcity inherent to mobile frameworks; standard models and even fine-tuned variants exhibit high compilation failure rates (over 54%) and negligible performance gains due to hallucinations and a lack of domain-specific grounding. To overcome these limitations, we propose the Mobile Kernel Agent (MoKA), a multi-agent system equipped with repository-aware reasoning and a plan-and-execute paradigm. Validated on MobileKernelBench, MoKA achieves state-of-the-art performance, boosting compilation success to 93.7% and enabling 27.4% of generated kernels to deliver measurable speedups over native libraries.

Related papers

• OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis [98.43366988856592]
  We present OpenMobile, an open-source framework that synthesizes high-quality task instructions and agent trajectories.<n>Agents trained on our data achieve competitive results across three dynamic mobile agent benchmarks.
  arXiv  Detail & Related papers  (2026-04-16T14:53:08Z)
• KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware [25.808580418841718]
  New AI accelerators often require developers to manually craft low-level kernels.<n>This prevents emerging hardware platforms from reaching the market efficiently.<n>We present KernelCraft: the first benchmark to evaluate an agent's ability to generate and optimize low-level kernels for customized accelerators.
  arXiv  Detail & Related papers  (2026-02-10T14:52:02Z)
• FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems [39.33711841865621]
  FlashInfer-Bench is a framework that connects kernel generation, benchmarking, and deployment.<n>Built on real serving traces, FlashInfer-Bench includes a curated dataset, a robust correctness- and performance-aware benchmarking framework, and a public leaderboard.<n>Using FlashInfer-Bench, we evaluate the performance and limitations of LLM agents, compare the trade-offs among different GPU programming languages, and provide insights for future agent design.
  arXiv  Detail & Related papers  (2026-01-01T06:18:53Z)
• MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning [91.90342432541138]
  Scaling up model size and training data has advanced foundation models for instance-level perception.<n>High computational cost limits adoption on resource-constrained platforms.<n>We introduce a new benchmark for efficient segmentation on both high-performance computing platforms and mobile devices.
  arXiv  Detail & Related papers  (2025-10-16T18:00:00Z)
• Agentic AI Reasoning for Mobile Edge General Intelligence: Fundamentals, Approaches, and Directions [74.35421055079655]
  Large language models (LLMs) have enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and autonomous decision-making capabilities.<n>Mobile Edge General Intelligence (MEGI) brings real-time, privacy-preserving reasoning to the network edge.<n>We propose a joint optimization framework for efficient LLM reasoning deployment in MEGI.
  arXiv  Detail & Related papers  (2025-09-27T10:53:48Z)
• Fed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuning [16.47223778897796]
  Large language models (LLMs) over heterogeneous mobile devices foster immense potential applications of personalized intelligence.<n> Conventional federated LLM FT approaches place prohibitive computational and memory burdens on mobile hardware.<n>We propose Fed MobiLLM, a novel design to facilitate efficient federated LLM FT across mobile devices with diverse computing/communication speeds and local model architectures.
  arXiv  Detail & Related papers  (2025-08-09T00:41:48Z)
• MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions [53.811953357289866]
  Large language models (LLMs) have shown remarkable progress across various domains.<n>LLMs struggle with incomplete code context understanding and inaccurate migration point identification.<n>MigGPT is a framework that employs a novel code fingerprint structure to retain code snippet information.
  arXiv  Detail & Related papers  (2025-04-13T08:08:37Z)
• Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices [5.926813659185372]
  Small-size large language models (LLMs) can run successfully on powerful mobile devices, though they exhibit quality limitations compared to larger models.<n>Only small-size LLMs can run successfully on powerful mobile devices, though they exhibit quality limitations compared to larger models.
  arXiv  Detail & Related papers  (2025-03-10T16:27:17Z)
• WDMoE: Wireless Distributed Mixture of Experts for Large Language Models [68.45482959423323]
  Large Language Models (LLMs) have achieved significant success in various natural language processing tasks. We propose a wireless distributed Mixture of Experts (WDMoE) architecture to enable collaborative deployment of LLMs across edge servers at the base station (BS) and mobile devices in wireless networks.
  arXiv  Detail & Related papers  (2024-11-11T02:48:00Z)
• PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms [11.87161637895978]
  We introduce our lightweight, all-in-one automated benchmarking framework that allows users to evaluate large language models on mobile devices.<n>We provide a benchmark of various popular LLMs with different quantization configurations (both weights and activations) across multiple mobile platforms with varying hardware capabilities.
  arXiv  Detail & Related papers  (2024-10-05T03:37:07Z)
• MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases [81.70591346986582]
  We introduce MobileAIBench, a benchmarking framework for evaluating Large Language Models (LLMs) and Large Multimodal Models (LMMs) on mobile devices. MobileAIBench assesses models across different sizes, quantization levels, and tasks, measuring latency and resource consumption on real devices.
  arXiv  Detail & Related papers  (2024-06-12T22:58:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.