I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems
Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority. We present evidence that integrity in institutional AI should be treated as a pre-deployment requirement rather than a post-deployment assumption. We evaluate multi-agent governance simulations in which agents occupy formal governmental roles under different authority structures, and we score rule-breaking and abuse outcomes with an independent rubric-based judge across 28,112 transcript segments. While we advance this position, the core contribution is empirical: among models operating below saturation, governance structure is a stronger driver of corruption-related outcomes than model identity, with large differences across regimes and model--governance pairings. Lightweight safeguards can reduce risk in some settings but do not consistently prevent severe failures. These results imply that institutional design is a precondition for safe delegation: before real authority is assigned to LLM agents, systems should undergo stress testing under governance-like constraints with enforceable rules, auditable logs, and human oversight on high-impact actions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions
We study the problem of stochastic bandits with adversarial corruptions in the cooperative multi-agent setting, where $V$ agents interact with a common $K$-armed bandit problem, and each pair of agents can communicate wi…
Multi-Armed BanditsOpen-Ended Question AnsweringMulti-Agent Stochastic Bandits Robust to Adversarial Corruptions
We study the problem of multi-agent multi-armed bandits with adversarial corruption in a heterogeneous setting, where each agent accesses a subset of arms. The adversary can corrupt the reward observations for all agents…
Multi-Armed BanditsSpeech Robust Bench: A Robustness Benchmark For Speech Recognition
As Automatic Speech Recognition (ASR) models become ever more pervasive, it is important to ensure that they make reliable predictions under corruptions present in the physical and digital world. We propose Speech Robust…
Adversarial RobustnessAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Robust Speech Recognition+2Corruption-free scheme of entering into contract: mathematical model
The main purpose of this paper is to formalize the modelling process, analysis and mathematical definition of corruption when entering into a contract between principal agent and producers. The formulation of the problem…
Improved Bounds for Private and Robust Alignment
In this paper, we study the private and robust alignment of language models from a theoretical perspective by establishing upper bounds on the suboptimality gap in both offline and online settings. We consider preference…