SMSota Moriyama

Sota Moriyama

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sota Moriyama has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    Talk Structurally, Act Hierarchically: A Collaborative Refinement Framework for LLM Multi-Agent Systems

    by Zhao Wang, Sota Moriyama, Wei-Yao Wang, Briti Gangopadhyay, Shingo Takamatsu

    While recent advancements in Large Language Model-based Multi-Agent (LLM-MA) systems have shown promise, significant challenges remain in managing communication and refinement when agents collaborate on complex tasks. In this paper, we propose Talk Structurally, Act Hierarchically (TalkHier), a novel framework that introduces a structured communication protocol for context-rich exchanges and a hierarchical refinement system to address issues such as incorrect outputs, falsehoods, and biases. TalkHier surpasses various types of SoTA, including inference scaling model (OpenAI-o1), open-source multi-agent models (e.g., AgentVerse), and majority voting strategies on current LLM and single-agent baselines (e.g., ReAct, GPT4o), across diverse tasks, including open-domain question answering, domain-specific selective questioning, and practical advertisement text generation. These results highlight its potential to set a new standard for LLM-MA systems, paving the way for more effective, adaptable, and collaborative multi-agent frameworks. The source code is available at https://github.com/sony/talkhier.


  • Open Access

    MOD-CL: Multi-label Object Detection with Constrained Loss

    by Sota Moriyama, Koji Watanabe, Katsumi Inoue, Akihiro Takemura

    We introduce MOD-CL, a multi-label object detection framework that utilizes constrained loss in the training process to produce outputs that better satisfy the given requirements. In this paper, we use $\mathrm{MOD_{YOLO}}$, a multi-label object detection model built upon the state-of-the-art object detection model YOLOv8, which has been published in recent years. In Task 1, we introduce the Corrector Model and Blender Model, two new models that follow after the object detection process, aiming to generate a more constrained output. For Task 2, constrained losses have been incorporated into the $\mathrm{MOD_{YOLO}}$ architecture using Product T-Norm. The results show that these implementations are instrumental to improving the scores for both Task 1 and Task 2.


  • GNN Based Extraction of Minimal Unsatisfiable Subsets

    by Sota Moriyama, Koji Watanabe, Katsumi Inoue