works on

From the 1 of 22 linked papers with an AI index.

collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI2026

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

Changyue Jiang, Wenqi Zhang, Xudong Pan +2

LLM-based agents solve complex tasks through iterative reasoning, tool use, and environment interaction, where each intermediate thought directly shapes subsequent actions. Small d…

cs.AI2026

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

Changyi Li, Pengfei Lu, Xudong Pan +2

As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators ar…

cs.AI2026

Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems

Yihe Fan, Wenqi Zhang, Xudong Pan +1

As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whe…

cs.AI2026

OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation

Yichen Wu, Qianqian Gao, Xudong Pan +2

As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequenc…

cs.AI2026

MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction

Wenqi Zhang, Yulin Shen, Changyue Jiang +3

Large foundation models are integrated into Computer Use Agents (CUAs), enabling autonomous interaction with operating systems through graphical user interfaces (GUIs) to perform c…

cs.AI2026

WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents

Xinyi Wu, Jiagui Chen, Geng Hong +4

Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present We…