5 papers · 1 filter
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Wanying Qu, Qinghua Mao, Yu Li +12
The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime contro…
A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions
Jianghan Shen, Siqi Luo, Yue Li +9
Policy gradient algorithms for language models optimize the same objective , which has exactly two factors: the trajectory probability…
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
Yu Li, Haoyu Luo, Yuejin Xie +10
Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or…
COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability
Yizhuo Ding, Mingkang Chen, Qiuhua Liu +7
Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: image…
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Lab, :, Yicheng Bao +115
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…