17 citations · 18 across the 15 of their papers we have counts for
15 papers
Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
Xutao Mao, Liangjie Zhao, Xiang Zheng +1
LLM agents increasingly save experience from past tasks as reusable skills through skill evolution. When an agent completes an unsafe task, skill evolution can keep the unsafe proc…
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents
Xutao Mao, Liangjie Zhao, Leyao Wang +6
Self-improving personal agents write profiles, memories, and reusable skills that carry over from one chat to the next. Prior works ask whether a model agrees with the user in its…
Agent Hacks Agents: Autoresearch Discovers Vulnerabilities in Production Agents
Xutao Mao, Xiang Zheng, Rui Qian +1
Production LLM agents such as Claude Code and Codex can modify files and execute commands, so safety failures become real destructive actions. Automatic red-teaming lets safety tea…
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
Xiao Li, Xiang Zheng, Yifeng Gao +35
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As…
STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
Xutao Mao, Liangjie Zhao, Tao Liu +3
Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generatio…
HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models
Zixing Chen, Yifeng Gao, Li Wang +8
Vision-Language-Action (VLA) models inherit rich world knowledge from vision-language backbones and acquire executable skills from action demonstrations. Yet current evaluations pr…
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
Xiang Zheng, Yutao Wu, Hanxun Huang +5
Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, th…
CALM: Curiosity-Driven Auditing for Large Language Models
Xiang Zheng, Longxiang Wang, Yi Liu +3
Auditing Large Language Models (LLMs) is a crucial and challenging task. In this study, we focus on auditing black-box LLMs without access to their parameters, only to the provided…
Constrained Intrinsic Motivation for Reinforcement Learning
Xiang Zheng, Xingjun Ma, Chao Shen +1
This paper investigates two fundamental problems that arise when utilizing Intrinsic Motivation (IM) for reinforcement learning in Reward-Free Pre-Training (RFPT) tasks and Explora…
Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy
Xiang Zheng, Xingjun Ma, Shengjie Wang +3
Reinforcement learning agents are susceptible to evasion attacks during deployment. In single-agent environments, these attacks can occur through imperceptible perturbations inject…
A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation
Yuxue Cao, Wenbo Zhao, Shengjie Wang +4
Symmetric bi-manual manipulation is an essential skill in on-orbit operations due to its potent load capacity. Previous works have applied compliant control to maintain the stabili…
A Policy Optimization Method Towards Optimal-time Stability
Shengjie Wang, Fengbo Lan, Xiang Zheng +5
In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization. However, these criter…
Reinforcement Learning with Prior Policy Guidance for Motion Planning of Dual-Arm Free-Floating Space Robot
Yuxue Cao, Shengjie Wang, Xiang Zheng +3
Reinforcement learning methods as a promising technique have achieved superior results in the motion planning of free-floating space robots. However, due to the increase in plannin…
A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object
Shengjie Wang, Yuxue Cao, Xiang Zheng +1
Recent years have seen the emergence of non-cooperative objects in space, like failed satellites and space junk. These objects are usually operated or collected by free-float dual-…
Clean-Label Backdoor Attacks on Video Recognition Models
Shihao Zhao, Xingjun Ma, Xiang Zheng +3
Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean tes…