MAEBE: Multi-Agent Emergent Behavior Framework
Traditional AI safety evaluations on isolated LLMs are insufficient as multi-agent AI ensembles become prevalent, introducing novel emergent risks. This paper introduces the Multi-Agent Emergent Behavior Evaluation (MAEBE) framework to systematically assess such risks. Using MAEBE with the Greatest Good Benchmark (and a novel double-inversion question technique), we demonstrate that: (1) LLM moral preferences, particularly for Instrumental Harm, are surprisingly brittle and shift significantly with question framing, both in single agents and ensembles. (2) The moral reasoning of LLM ensembles is not directly predictable from isolated agent behavior due to emergent group dynamics. (3) Specifically, ensembles exhibit phenomena like peer pressure influencing convergence, even when guided by a supervisor, highlighting distinct safety and alignment challenges. Our findings underscore the necessity of evaluating AI systems in their interactive, multi-agent contexts.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior
In this work, we integrate `social' interactions into the MARL setup through a user-defined relational network and examine the effects of agent-agent relations on the rise of emergent behaviors. Leveraging insights from …
Multi-agent Reinforcement LearningSociologySimulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning
Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-wo…
Imitation LearningUsing Neural Networks for Programming by Demonstration
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specif…
Analytical Swarm Chemistry: Characterization and Analysis of Emergent Swarm Behaviors
Swarm robotics has potential for a wide variety of applications, but real-world deployments remain rare due to the difficulty of predicting emergent behaviors arising from simple local interactions. Traditional engineeri…
Group Cohesion in Multi-Agent Scenarios as an Emergent Behavior
In this paper, we elaborate on the design and discuss the results of a multi-agent simulation that we have developed using the PSI cognitive architecture. We demonstrate that imbuing agents with intrinsic needs for group…