2 papers
cs.MA2026
Designing for Accountable Agents: a Viewpoint
Stephen Cranefield, Nir Oren
AI systems are becoming increasingly complex, ubiquitous and autonomous, leading to increasing concerns about their impacts on individuals and society. In response, researchers hav…
cs.MA2026
Evaluating LLM Alignment With Human Trust Models
Anushka Debnath, Stephen Cranefield, Bastin Tony Roy Savarimuthu +1
Trust plays a pivotal role in enabling effective cooperation, reducing uncertainty, and guiding decision-making in both human interactions and multi-agent systems. Although it is s…