Shun-ichiro Hayashi

Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino et al.

In LLM-based code generation, multiple code candidates are often generated in parallel from the same prompt -- for example, in best-of-N sampling or multi-candidate code completion. These requests can share KV caches through a common prefix, yet the extent to which their Mixture-of-Experts (MoE) expert routing overlaps, and how this overlap varies across layers, remains insufficiently understood. We study Qwen3.5-35B-A3B-FP8 (256 routed experts, top-8) by performing tree-search-based branching generation from a shared prefix (851 completed codes, temperature 0.7) and analyzing the results with a compiler-output-based alignment (gcc -S -O0 assembly) that controls for token-identity confounds. Our findings are threefold: (1) At positions where both sequences generated the same token, Jaccard similarity reaches 0.649 (40x random), while even at positions with different tokens it remains 0.175 (11x random). (2) A layer-wise decomposition reveals a crossing pattern: same-token routing similarity exceeds different-token similarity across all layers, but dips in the middle layers (L14-20), while different-token similarity peaks in the middle layers at 14x random. (3) In tree-search code generation, 67% of successfully compiled codes concentrate in the top three assembly-equivalent groups, and 99.6% of within-group differences consist of comments and blank lines. We show that diversity in top-P search, including beam search, poses a significant challenge. These results refine the "context-independent routing" claim of prior work through layer-wise decomposition and suggest opportunities for improving search efficiency in LLM code generation.

Ryo Mikasa, Shun-ichiro Hayashi, Daichi Mukunoki et al.

Large language models (LLMs) have demonstrated strong code generation capabilities, yet the runtime performance of generated code is not guaranteed, and there have been few attempts to train LLMs using runtime performance as a reward in the HPC domain. We propose an online reinforcement learning approach that executes LLM-generated code on a supercomputer and directly feeds back the measured runtime performance (GFLOPS) as a reward. We further introduce a Staged Quality-Diversity (SQD) algorithm that progressively varies the permitted optimization techniques on a per-problem basis, enabling the model to learn code optimization from diverse perspectives. We build a distributed system connecting a GPU training cluster with a CPU benchmarking cluster, and train Qwen2.5 Coder 14B on a double-precision matrix multiplication task using Group Relative Policy Optimization (GRPO). Through two experiments, we show that reinforcement learning combining runtime performance feedback with staged optimization can improve the HPC code generation capability of LLMs.

Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino et al.

This paper proposes "3Dify," a procedural 3D computer graphics (3D-CG) generation framework utilizing Large Language Models (LLMs). The framework enables users to generate 3D-CG content solely through natural language instructions. 3Dify is built upon Dify, an open-source platform for AI application development, and incorporates several state-of-the-art LLM-related technologies such as the Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG). For 3D-CG generation support, 3Dify automates the operation of various Digital Content Creation (DCC) tools via MCP. When DCC tools do not support MCP-based interaction, the framework employs the Computer-Using Agent (CUA) method to automate Graphical User Interface (GUI) operations. Moreover, to enhance image generation quality, 3Dify allows users to provide feedback by selecting preferred images from multiple candidates. The LLM then learns variable patterns from these selections and applies them to subsequent generations. Furthermore, 3Dify supports the integration of locally deployed LLMs, enabling users to utilize custom-developed models and to reduce both time and monetary costs associated with external API calls by leveraging their own computational resources.

Shun-ichiro Hayashi, Koki Morita, Daichi Mukunoki et al.

We propose VibeCodeHPC, an automatic tuning system for HPC programs based on multi-agent LLMs for code generation. VibeCodeHPC tunes programs through multi-agent role allocation and iterative prompt refinement. We describe the system configuration with four roles: Project Manager (PM), System Engineer (SE), Programmer (PG), and Continuous Delivery (CD). We introduce dynamic agent deployment and activity monitoring functions to facilitate effective multi-agent collaboration. In our case study, we convert and optimize CPU-based matrix-matrix multiplication code written in C to GPU code using CUDA. The multi-agent configuration of VibeCodeHPC achieved higher-quality code generation per unit time compared to a solo-agent configuration. Additionally, the dynamic agent deployment and activity monitoring capabilities facilitated more effective identification of requirement violations and other issues.

Daichi Mukunoki, Shun-ichiro Hayashi, Tetsuya Hoshino et al.

Generative AI technology based on Large Language Models (LLM) has been developed and applied to assist or automatically generate program codes. In this paper, we evaluate the capability of existing general LLMs for Basic Linear Algebra Subprograms (BLAS) code generation for CPUs. We use two LLMs provided by OpenAI: GPT-4.1, a Generative Pre-trained Transformer (GPT) model, and o4-mini, one of the o-series of Reasoning models. Both have been released in April 2025. For the routines from level-1 to 3 BLAS, we tried to generate (1) C code without optimization from routine name only, (2) C code with basic performance optimizations (thread parallelization, SIMD vectorization, and cache blocking) from routine name only, and (3) C code with basic performance optimizations based on Fortran reference code. As a result, we found that correct code can be generated in many cases even when only routine name are given. We also confirmed that thread parallelization with OpenMP, SIMD vectorization, and cache blocking can be implemented to some extent, and that the code is faster than the reference code.