Conference-Paper

ScenarioBench: Trace-Grounded Compliance Evaluation for Text-to-SQL and RAG
ScenarioBench is a policy-grounded, trace-aware benchmark for evaluating Text-to-SQL and retrieval-augmented generation in compliance …
Cite DOI
A Reflective Architecture for LLM-Based Systems
Modern artificial intelligence (AI) systems critically lack the ability to reflect on their own behavior, reasoning processes, and …
Cite DOI
Empirical Expectations and Coordination Games
Coordination is a central challenge in self-organizing multi-agent and sociotechnical systems, especially as control shifts from …
Cite DOI
The Social Life of ChatGPT: Insights From TikTok
ChatGPT is reshaping ideas of agency, companionship, and emotional intelligence in a post digital world. Research has often focused on …
Cite DOI
Evaluating the Trustworthiness of User-Generated Content on Social Media
Despite the extensive research on digital consumer engagement, the dimension of trust in user-generated content (UGC) on social media …
Cite DOI
Transfer Learning Can Introduce Bias
Transfer learning involves leveraging knowledge gained from solving one task and then using that knowledge to improve performance and …
Cite DOI
Incorporating Social Expectations into the Expectation Event Calculus
This paper focuses on the internal representation of norms and the necessary concepts required for normative decisionmaking in …
Cite DOI
Towards Reflective Normative Agents
An ‘Interdisciplinary Frontier’ of norm research has emerged within the social sciences, carrying forward a wave of new theories and …
Cite DOI
The Triangles of Dishonesty: Modelling the Evolution of Lies, Bullshit, and Deception in Agent Societies
Misinformation and disinformation in agent societies can be spread due to the adoption of dishonest communication. Recently, this …
Cite DOI
Self-awareness in Cyber-Physical Systems: Recent Developments and Open Challenges
Self-aware computing systems enable computing systems to reflect on their actions and behavior. This becomes even more relevant in …
Cite DOI