10 papers
ClashBench: Conflicts Leading Agents to Seize and Harm
Yuejin Xie, Yu Li, Dadi Guo +6
As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing resources with limited capacit…
PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
Yusong Zhao, Yuejin Xie, Youliang Yuan +4
Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible. Video-capable multimodal large language mod…
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…
Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex
Zhonghao Yang, Yu Li, Yanxu Zhu +6
As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse…
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Qihan Ren, Peng Wang, Ruikun Cai +8
A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT…
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…
Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?
Dadi Guo, Yuejin Xie, Qingyu Liu +11
As large language models (LLMs) advance their mathematical capabilities toward the IMO and research level, the scarcity of challenging, high-quality problems has become a significa…
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian +40
The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk…
Towards Evaluating Proactive Risk Awareness of Multimodal Language Models
Youliang Yuan, Wenxiang Jiao, Yuejin Xie +5
Human safety awareness gaps often prevent the timely recognition of everyday risks. In solving this problem, a proactive safety artificial intelligence (AI) system would work bette…
Enhancing the Accuracy and Comprehensibility in Architectural Tactics Detection via Small Model-Augmented Prompt Engineering
Lingli Cao, He Zhang, Shanshan Li +5
Architectural tactics (ATs), as the concrete implementation of architectural decisions in code, address non-functional requirements of software systems. Due to the implicit nature…