Sota Moriyama
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
Research Subjects
Sota Moriyama has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Katsumi Inoue
National Institute of Informatics
2 shared publications - Koji Watanabe
National Institute of Informatics Tokyo Japan
2 shared publications - Akihiro Takemura
National Institute of Informatics, Tokyo, Japan
1 shared publication - Briti Gangopadhyay
Sony Group Corporation, Tokyo, Japan
1 shared publication - Shingo Takamatsu
Sony Group Corporation, Tokyo, Japan
1 shared publication - Wei-Yao Wang
Sony Group Corporation, Tokyo, Japan
1 shared publication
Latest Publications
- Top Cited Papers
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (9) , 1-11
Talk Structurally, Act Hierarchically: A Collaborative Refinement Framework for LLM Multi-Agent Systems
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.
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (9) , 1-11
Top Cited PapersTalk Structurally, Act Hierarchically: A Collaborative Refinement Framework for LLM Multi-Agent Systems
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
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.Open AccessMOD-CL: Multi-label Object Detection with Constrained Loss
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. - 22 December 2023
- Published by Springer Nature
- p. 77-92
GNN Based Extraction of Minimal Unsatisfiable Subsets
- 22 December 2023
- Published by Springer Nature
- p. 77-92
GNN Based Extraction of Minimal Unsatisfiable Subsets