arXiv subjects

So Morikawa

Publications and source records attributed to So Morikawa.

3 recordsLinked to original sources

arXiv2025

AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots

AGENTiGraph is a user-friendly, agent-driven system that enables intuitive interaction and management of domain-specific data through the manipulation of knowledge graphs in natural language. It gives non-technical users a complete, visual solution to incrementally build and refine their knowledge bases, allowing multi-round dialogues and dynamic updates without specialized query languages. The flexible design of AGENTiGraph, including intent classification, task planning, and automatic knowledge integration, ensures seamless reasoning between diverse tasks. Evaluated on a 3,500-query benchmark within an educational scenario, the system outperforms strong zero-shot baselines (achieving 95.12% classification accuracy, 90.45% execution success), indicating potential scalability to compliance-critical or multi-step queries in legal and medical domains, e.g., incorporating new statutes or research on the fly. Our open-source demo offers a powerful new paradigm for multi-turn enterprise knowledge management that bridges LLMs and structured graphs.

cs.AI↗

arXiv2024

Collaborative Participatory Research with LLM Agents in South Asia: An Empirically-Grounded Methodological Initiative and Agenda from Field Evidence in Sri Lanka

The integration of artificial intelligence into development research methodologies presents unprecedented opportunities for addressing persistent challenges in participatory research, particularly in linguistically diverse regions like South Asia. Drawing from an empirical implementation in Sri Lanka's Sinhala-speaking communities, this paper presents an empirically grounded methodological framework designed to transform participatory development research, situated in the challenging multilingual context of Sri Lanka's flood-prone Nilwala River Basin. Moving beyond conventional translation and data collection tools, this framework deploys a multi-agent system architecture that redefines how data collection, analysis, and community engagement are conducted in linguistically and culturally diverse research settings. This structured agent-based approach enables participatory research that is both scalable and responsive, ensuring that community perspectives remain integral to research outcomes. Field experiences reveal the immense potential of LLM-based systems in addressing long-standing issues in development research across resource-limited regions, offering both quantitative efficiencies and qualitative improvements in inclusivity. At a broader methodological level, this research agenda advocates for AI-driven participatory research tools that maintain ethical considerations, cultural respect, and operational efficiency, highlighting strategic pathways for deploying AI systems that reinforce community agency and equitable knowledge generation, potentially informing broader research agendas across the Global South.

cs.CY↗

arXiv2017

Evolution of favoritism and group fairness in a co-evolving three-person ultimatum game

The evolution of fairness in dyadic relationships has been studied using ultimatum games. However, human fairness is not limited to two-person situations and universal egalitarianism among group members is widely observed. In this study, we investigated the evolution of favoritism and group fairness in a three-person ultimatum game (TUG) under a co-evolutionary framework with both strategy updating and partner switching dynamics. In the TUG, one proposer makes an offer to two responders and the proposal is accepted at the group level if at least one individual responder accepts the offer. Investigating fairness beyond dyadic relationships allows the possibility of favoritism because the proposer can secure acceptance at the group level by discriminating in favor of one responder. Our simulation showed that the proposer favors one responder with a similar type when the frequency of partner switching is low. In contrast, group fairness is observed when the frequency of partner switching is high. The correlation between strategy and neighborhood size suggested that partner switching influences the strategy through the proposer's offer rather than through the responder's acceptance threshold. In addition, the average degree negatively impacts the emergence of fairness unless the frequency of partner switching is high. Furthermore, a higher frequency of partner switching can support the evolution of fairness when the maximum number of games in one time step is restricted to smaller values.

physics.soc-ph↗