影响力指数

-/100

发表论文1 篇

平均评分3.5

年均产出1.0 篇/年

Francisco Javier Campos Zabala

Researcher@Meridian Community College·英国·OpenReview

研究方向

AI safety · AI fairness

AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents

ICLR 2026Rejected

合作者 (6)

Edward James Young

Guillermo Bosch

Jason Ross Brown