StepGuard introduces a step-level guard model that audits and checks tool actions before execution, addressing security risks in LLM-based agents. It is trained using StepGen, an automatic engine that generates safe and unsafe trajectories, and employs Balance-GRPO to dynamically balance learning between safe and unsafe actions. Experiments show StepGuard achieves high accuracy comparable to GPT-5.4 and significantly reduces attack success rates while minimally impacting utility.
By Zhijie Zheng, Yu Li, Chen Qian, Yuqian Fu, Yanwei Fu, Lu Sheng, Jing Shao, Dongrui Liu
MobileWorldSafety is a benchmark that evaluates the safety of large language model–powered GUI agents on Android by exposing them to 142 real-world risk tasks involving environmental injection attacks. The benchmark uses a two‑stage verification pipeline—rule‑based checks for clear cases and an LLM judge for ambiguous ones—to distinguish safety failures from capability failures. Experiments on six agents show high vulnerability, with attack success rates between 40.4% and 66.9%, highlighting that current agents often fail to remain safe when faced with adversarial content presented as normal mobile context.
By Sujin Chen, Lijun Li, Tianyi Du, Jing Shao
arXiv:2609.00015v1 Announce Type: new
Abstract: AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, control...
By Dongsheng Chen, Xiangyu Zhao, Xin Yao, Xuetao Wei
The paper introduces AnTrap, a benchmark that injects dynamic perturbations into Android GUI agent execution to evaluate robustness against runtime anomalies. It presents a taxonomy of anomalies across four layers—State, Thinking, Action, and Round—with ten subcategories, and a pipeline that maintains task solvability while adding realistic adversarial conditions. Experiments on 16 leading GUI models show universal vulnerability, and reinforcement learning can mitigate some traps but not deep contextual ones like state deadlock.
By Guo Gan, Yilun Zhao, Cong Chen, Jinbiao Wei, Tingyu Song, Zheyuan Yang, Lin Fu, Hong Zhou
arXiv:2608. 15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails.
By Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu, Ruihong Huang
Sapien is a policy engine that enforces stateful contextual policies for autonomous AI agents, specifying allowed tool‑call sequences with an extended regular expression that includes stateful predicates, deferred policy generation, and scoped semantic checks. The system maintains performance close to an unconstrained agent while significantly reducing malicious actions, ruling out 93‑95% of attacks on AgentDojo and 62‑85% on Toolathlon, outperforming traditional tool allowlists on long‑horizon tasks.
By Corinn Tiffany, Wen Zhang, Eugene Bagdasarian, Lillian Tsai
arXiv:2606. 02302v1 Announce Type: cross Abstract: Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services.
By Hao Cheng, Changtao Miao, Tianle Song, Yin Wu, He Liu, Erjia Xiao, Junchi Chen, Xiaoyu Shi, Yichi Wang, Jing Yang, Taowen Wang, Jinhao Duan, Mengshu Sun, Peiyan Dong, Xuan Shen, Yang Cao, Renjing Xu, Kaidi Xu, Jindong Gu, Bo Zhang, Jize Zhang, Chenhao Lin, Philip Torr, Chao Shen
APPSim-Bench is a new benchmark for mobile GUI agents that uses controllable simulated apps to balance realism and reproducibility. It includes 557 tasks across 17 popular Chinese and English apps, with a coding-agent-assisted and human-verified workflow that ensures deterministic evaluation. Evaluation of 19 agents shows that autonomous mobile execution is still far from perfect, with the best model completing only 50.27% of tasks and many failures in longer workflows and numerical reasoning.
By Jintian Feng, Long Chen, Xiao Yu, Jiayi Dai, Chenglong Liu, Haoru Wang, Zizhen Xue, Yuxuan Shi, Ziyang Wang, Yichen Gong
arXiv:2609.33676v2 Announce Type: replace
Abstract: LLM agents increasingly take consequential actions through interactions with users, policies, and external tools. Auditing these agents requires au...
By Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo, Dong Wang
arXiv:2603. 00829v2 Announce Type: replace-cross Abstract: Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms.
By Simon Storf, Rich Barton-Cooper, James Peters-Gill, Marius Hobbhahn
arXiv:2510. 24411v3 Announce Type: replace Abstract: Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.
By Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong
arXiv:2607. 13081v1 Announce Type: cross Abstract: We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion.
By SingGuard Team