影响力指数

33.1/100

前 21%

全站排名 #13,523

发表论文4 篇

平均评分6.0

年均产出2.0 篇/年

Boyi Wei

PhD student@Princeton University·美国·OpenReview

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

ICLR 2026Poster

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

ICLR 2026Poster

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

ICLR 2025Poster

On Evaluating the Durability of Safeguards for Open-Weight LLMs

ICLR 2025Poster

合作者 (20)

Peter Henderson

博士导师3 篇