5 papers
Artificial collectives of specialists and generalists excel at different tasks
John Meluso, Laurent Hébert-Dufresne, Christoph Riedl +1
Collective artificial intelligence, where multiple agents work on shared tasks, holds potential to solve expansive problems in fields from medicine to collective governance. But wh…
Emergent Coordination in Multi-Agent Language Models
Christoph Riedl
When are multi-agent LLM systems merely a collection of individual agents versus an integrated collective with higher-order structure? We introduce an information-theoretic framewo…
Language Models use Lookbacks to Track Beliefs
Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma +5
How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mi…
Agents of Chaos
Natalie Shapira, Chris Wendler, Avery Yen +35
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord acc…
Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs
Sean W. Kelley, Christoph Riedl
Large Language Models (LLMs) are prone to sycophantic behavior, uncritically conforming to user beliefs. As models increasingly condition responses on user-specific context (person…