6 citations · 8 across the 27 of their papers we have counts for
31 papers
Information-Gain Calibrated On-Policy Distillation for Deep Search Agents
Chenxi Li, Xueyang Feng, Songyang Liu +4
On-policy distillation (OPD) has recently emerged as a promising approach for transferring the capabilities of large agents to compact students. In deep search, where agents iterat…
A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors
Pengxun Li, Litian Zhang, Jianwei Hou +4
Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These commands run with host privileg…
GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities
Haoran Bu, Zejian Chen, Litian Zhang +1
LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers may mani…
Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents
Bingyu Yan, Xiaoming Zhang, Chaozhuo Li +3
Self-evolving large language model agents improve their capabilities by distilling interaction trajectories into persistent experiences. Yet this mechanism introduces a new safety…
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
Longzhu He, Peng Tang, Chaozhuo Li +5
Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain con…
OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks
Litian Zhang, Chaozhuo Li, Yuting Zhang +3
LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication…
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS
Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4
While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools,…
PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4
LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and collaborative reasoning. Howev…
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
Zejian Chen, Zhanyuan Liu, Chaozhuo Li +6
Computer-use agents(CUAs)are moving frombounded benchmarks toward real software environments, wherethey operate browsers, desktops, mobile applications, flesystems,terminals, and t…
Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents
Haoran Bu, Litian Zhang, Chuxuan Zhang +3
Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade social bot detection. However, whi…
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Songyang Liu, Chaozhuo Li, Chenxu Wang +8
OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell c…
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies
Chenxu Wang, Chaozhuo Li, Songyang Liu +10
The emergence of multi-agent systems built from large language models (LLMs) offers a promising paradigm for scalable collective intelligence and self-evolution. Ideally, such syst…
From static to adaptive: immune memory-based jailbreak detection for large language models
Jun Leng, Yu Liu, Litian Zhang +3
Large Language Models (LLMs) serve as the backbone of modern AI systems, yet they remain susceptible to adversarial jailbreak attacks. Consequently, robust detection of such malici…
Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
Zejian Chen, Chaozhuo Li, Chao Li +3
This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilit…
How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference
Songyang Liu, Chaozhuo Li, Rui Pu +5
Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications tha…
LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs
Chenxu Wang, Chaozhuo Li, Pengbo Wang +7
Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to…
Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Bingyu Yan, Ziyi Zhou, Xiaoming Zhang +5
Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantia…
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
Rui Pu, Chaozhuo Li, Rui Ha +3
Defending large language models (LLMs) against jailbreak attacks is essential for their safe and reliable deployment. Existing defenses often rely on shallow pattern matching, whic…
LLMs are Introvert
Litian Zhang, Xiaoming Zhang, Bingyu Yan +5
The exponential growth of social media and generative AI has transformed information dissemination, fostering connectivity but also accelerating the spread of misinformation. Under…
Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
Chaozhuo Li, Pengbo Wang, Chenxu Wang +7
Edgar Allan Poe noted, "Truth often lurks in the shadow of error," highlighting the deep complexity intrinsic to the interplay between truth and falsehood, notably under conditions…
Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction
Zhihao Tang, Chaozhuo Li, Litian Zhang +1
Early prediction of Mild Cognitive Impairment (MCI) conversion is hampered by a trade-off between immediacy--making fast predictions from a single baseline sMRI--and accuracy--leve…
Lifelong Evolution: Collaborative Learning between Large and Small Language Models for Continuous Emergent Fake News Detection
Ziyi Zhou, Xiaoming Zhang, Litian Zhang +4
The widespread dissemination of fake news on social media has significantly impacted society, resulting in serious consequences. Conventional deep learning methodologies employing…
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
Songyang Liu, Chaozhuo Li, Jiameng Qiu +5
With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), including content gener…
One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
Pengbo Wang, Chaozhuo Li, Chenxu Wang +3
LLMs have demonstrated unprecedented capabilities in natural language processing, yet their practical deployment remains hindered by persistent factuality and faithfulness hallucin…