Jayalakshmi Baskar | PhD Research

About Me

I am a PhD student in Computing Science at Umeå University, Sweden, working under the supervision of Prof. Helena Lindgren. My research focuses on adaptive human-agent dialogues, argumentation-based interaction, personalised support, and collaborative reasoning in health and well-being contexts.

My doctoral research investigates how software agents can support people through personalised storytelling, purposeful dialogue, collaborative reasoning, and reflective behaviour, with applications in personalised support for older adults on health-related topics.

PhD Thesis

Working Thesis Title

Adaptive Human-Agent Dialogues for Collaborative Reasoning and Decision-Making

Thesis Focus

This thesis investigates adaptive human-agent dialogues for collaborative reasoning and decision-making in the context of personalised support for older adults on health-related topics.

The research explores how software agents can engage in purposeful dialogues that support reflection, planning, behaviour change, and collaborative reasoning. A central challenge is enabling agents to adapt to individual users, manage dialogue goals, reason about motives and activities, and personalise interactions over time.

The thesis combines cognitive agent architectures, argumentation-based dialogue, personalised storytelling, argument mining, and agent self-reflection to support meaningful human-agent collaboration.

Human-Agent Dialogue Collaborative Reasoning Argumentation Personalised Storytelling Agent Self-Reflection Older Adults Health and Well-being

Research Questions

How can knowledge about users, activities, goals, motives, dialogue purposes, and context be represented to support adaptive human-agent dialogues? (Papers III, IV)
How can cognitive agent architectures use such knowledge to support collaborative reasoning and decision-making through adaptive dialogues? (Papers I, II)
How can adaptive dialogue agents support personalised health-related reflection and planning through argumentation, storytelling, and self-reflective mechanisms? (Papers V, VI)
How are such adaptive dialogue agents perceived and evaluated by domain experts and older adults? (Papers II, V, VI)

Objectives

Design and implement a cognitive architecture supporting adaptive human-agent dialogues.
Develop knowledge models and dialogue mechanisms for collaborative reasoning and decision-making.
Extend the architecture with personalised storytelling, argumentation, argument mining, and agent self-reflection capabilities.
Evaluate the proposed approaches through empirical studies involving domain experts and older adults.

Thesis Contributions

The main contributions of the thesis are:

A designed and implemented BDI-based cognitive architecture for adaptive human-agent dialogues, where the knowledge base includes knowledge about users, activities, motives, goals, dialogue purposes, and contextual factors. The architecture integrates reasoning, planning, adaptation, and dialogue management mechanisms.
A method for combining four types of argument-based dialogues with different purposes within a unified framework for collaborative dialogue activity.
Empirical findings on how domain experts and older adults perceive, evaluate, and collaborate with adaptive dialogue agents in health-related contexts.
An extension of the architecture with methods and technology that combine LLM-based personalised storytelling with argumentation, and embed agent self-reflection through argument mining.

Included Thesis Papers

Paper I. Cognitive Architecture of an Agent for Human-Agent Dialogues

Jayalakshmi Baskar and Helena Lindgren. Cognitive Architecture of an Agent for Human-Agent Dialogues. In Highlights of Practical Applications of Heterogeneous Multi-Agent Systems. The PAAMS Collection. Communications in Computer and Information Science, vol. 430, pp. 89–100. Springer, 2014.

PDF

Paper II. Human-Agent Dialogues on Health Topics: An Evaluation Study

Jayalakshmi Baskar and Helena Lindgren. Human-Agent Dialogues on Health Topics: An Evaluation Study. In Highlights of Practical Applications of Agents, Multi-Agent Systems, and Sustainability. Communications in Computer and Information Science, vol. 524, pp. 28–39. Springer, 2015.

PDF

Paper III. Instrument-Oriented Approach to Detecting and Representing Human Activity for Supporting Executive Functions and Learning

Jayalakshmi Baskar, Chunli Yan, and Helena Lindgren. Instrument-Oriented Approach to Detecting and Representing Human Activity for Supporting Executive Functions and Learning. In Proceedings of the European Conference on Cognitive Ergonomics, pp. 105–112. ACM, 2017. DOI: 10.1145/3121283.3121305.

PDF

Paper IV. A Multipurpose Goal Model for Personalised Digital Coaching

Jayalakshmi Baskar, Rebecka Janols, Esteban Guerrero, Juan Carlos Nieves, and Helena Lindgren. A Multipurpose Goal Model for Personalised Digital Coaching. In Agents and Multi-Agent Systems for Health Care. Lecture Notes in Computer Science, vol. 10685, pp. 94–116. Springer, 2017.

PDF

Paper V. Understanding Human-Diary Agent Collaboration through an Activity-Theoretical Framework

Jayalakshmi Baskar, Vera C. Kaelin, and Helena Lindgren. Understanding Human-Diary Agent Collaboration through an Activity-Theoretical Framework. Manuscript submitted to the Journal of Ambient Intelligence and Humanized Computing special issue, 2026.

Manuscript under review

PDF

Paper VI. A Reflective Storytelling Agent for Older Adults

Jayalakshmi Baskar, Vera C. Kaelin, Kaan Kilic, and Helena Lindgren. A Reflective Storytelling Agent for Older Adults: Integrating Argumentation Schemes and Argument Mining in LLM-Based Personalised Narratives. Manuscript under major revision for ACM Transactions on Intelligent Systems and Technology special issue, 2026.

Major revision

PDF

Other Publications

Jayalakshmi Baskar, Vera C. Kaelin, and Helena Lindgren. Experts' Perception of AI-Generated Personalised Stories for Health Promotion. Studies in Health Technology and Informatics, vol. 336, pp. 660–664, 2026. DOI: 10.3233/SHTI260253. PDF
Jayalakshmi Baskar, Kaan Kilic, Vera C. Kaelin, and Helena Lindgren. Towards Collaborative Planning for Health Promotion through Person-Tailored Storytelling and Argumentation. In 1st Workshop on Human-AI Collaborative Systems, co-located with ECAI 2025, CEUR Workshop Proceedings, vol. 4072, 2025. PDF
Helena Lindgren, Jayalakshmi Baskar, Esteban Guerrero, Juan Carlos Nieves, Ingeborg Nilsson, and Chunli Yan. Computer-Supported Assessment for Tailoring Assistive Technology. In Proceedings of the 6th ACM International Conference on Digital Health, pp. 1–10, 2016. PDF
Juan Carlos Nieves, Esteban Guerrero, Jayalakshmi Baskar, and Helena Lindgren. Deliberative Argumentation for Smart Environments. In PRIMA 2014: Principles and Practice of Multi-Agent Systems, pp. 141–149, 2014. PDF
Jayalakshmi Baskar, Helena Lindgren, Chunli Yan. User's Control of Personalised Intelligent Environments Supporting Health. In Proceedings of the 9th International Conference on Intelligent Environments, pp. 270–273. IEEE, 2013. PDF
Helena Lindgren, Farahnaz Yekeh, Jayalakshmi Baskar, and Chunli Yan. Agent-Supported Assessment for Personalized Ambient Assisted Living. In Workshop on Agents Applied in Health Care, pp. 141–150, 2012. PDF
Jayalakshmi Baskar, Helena Lindgren, Chunli Yan. Personalisation and User Models for Support in Daily Living. In The 27th Annual Workshop of the Swedish Artificial Intelligence Society, pp. 7–15, 2012. PDF

Awards

2014: Award of Scientific Excellence for the paper Cognitive Architecture of an Agent for Human-Agent Dialogues, PAAMS 2014.

Contact

Email: jaya@cs.umu.se

Website: jayalakshmibaskar.com