8 papers
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types
Hadas Orgad, Boyi Wei, Kaden Zheng +4
Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning o…
Scaling Latent Reasoning via Looped Language Models
Rui-Jie Zhu, Zixuan Wang, Kai Hua +30
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training…
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
Shuai Shao, Qihan Ren, Chen Qian +8
Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the environment, demonstrating strong c…
Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
Boyi Wei, Zora Che, Nathaniel Li +10
Open-weight bio-foundation models present a dual-use dilemma. While holding great promise for accelerating scientific research and drug development, they could also enable bad acto…
Dynamic Risk Assessments for Offensive Cybersecurity Agents
Boyi Wei, Benedikt Stroebl, Jiacen Xu +3
Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier…
Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
Sayash Kapoor, Benedikt Stroebl, Peter Kirgis +28
AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of…