This paper introduces The Energy Society, a simulation environment where LLM agents spend energy to generate tokens, regain energy through jobs or donations, and face survival pressure under competitive or cooperative incentives.
This paper introduces the Arbiter, an agent that monitors multi-agent conversations under an inspection budget and uses active inspection tools to detect misaligned agents earlier and more accurately.
This paper introduces PsychoSafe, a refusal framework grounded in evidence-based intervention strategies, and evaluates prompting and fine-tuning approaches for psychologically informed LLM refusals.
This paper studies emergent languages in Moltbook agent populations, identifying categories such as token efficiency, new natural languages, and oversight evasion, and showing that surface-behavior monitoring may be insufficient for agent oversight.
This paper evaluates six confidence-estimation methods for activation oracles and finds that bootstrap mode frequency is the best-calibrated method among those tested, while log-probability can serve as a cheaper triage signal.
This paper releases and analyzes the Moltbook Files, a dataset of agent-only social-network activity, studying community structure, safety risks, and the effect of Moltbook data on downstream language-model behavior.
A 24-hour comprehensive online course on Generative AI fundamentals, Large Language Models, practical prompt engineering, and AI safety best practices for Comune di Torino staff.
This study introduces the Author-Reviewer-Organizer (ARO) framework and presents a large-scale empirical assessment of indirect prompt injection in AI-assisted peer review, finding that hidden instructions are followed in 78% of cases for ChatGPT and 86% for Gemini.