4 papers
SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
Qinghua Mao, Wanying Qu, Dadi Guo +8
The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmfu…
PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning
Qihao Lin, Guanxu Chen, Dongrui Liu +1
As LLMs continue to scale up, improving training efficiency heavily relies on effective data utilization. Data selection mitigates this issue by allocating the limited training bud…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
Guanxu Chen, Jing Shao, Tao Luo +3
Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain unclear. Chain-of-thoughts (CoTs) have bee…