A Stanford University paper introduces Self-Organizing Agent Teams (SAT), a framework in which groups of AI agents learn collaboration strategies from as few as 15 AIME 2024 or 25 GPQA Diamond problem…
A World Values Survey-grounded simulation of LLM agent societies found that more than 50% of personas fail to express their assigned WVS value profiles from the outset, while only 2-7% drift after rep…
Google researchers propose embedding the Universal Declaration of Human Rights into AI training pipelines as a forward-alignment technique for agentic AI, testing their Human Rights Taxonomy against 1…
Researchers introduced FirstResearch, a framework that generates auditable research questions for LLM scientific discovery agents by producing a structured Research Question Certificate. In evaluation…