565 citations · 621 across the 39 of their papers we have counts for
45 papers
Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees
Wenbin Hu, Huihao Jing, Haochen Shi +9
Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an auto-regressive guardrail model remains challenging: such mod…
Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
Huihao Jing, Shaojin Chen, Wenbin Hu +5
As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardrails are…
SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
Yuxuan Liu, Haoran Li, Yuhao Zhang +10
Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaking correct b…
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning
Wenbin Hu, Huihao Jing, Haochen Shi +3
Group Relative Policy Optimization (GRPO) is widely used to train reasoning language models, where it computes advantages by centering and normalizing rewards across rollouts of th…
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
Yuxuan Liu, Zhaochen Su, Yuhao Zhang +9
Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model. Yet it remains unclear when…
RLPF: Reinforcement Learning from Performance Feedback for Code Generation
Huihao Jing, Haozhe Cui, Wenbin Hu +9
Code models are increasingly trained with execution feedback, but most training signals still stop at correctness. This leaves an important gap for systems code: two programs can p…
Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions
Huihao Jing, Wenbin Hu, Shaojin Chen +10
The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only…
Steering LLM Viewpoints through Fabricated Evidence Injection
Xi Yang, Chang Liu, Zhenglin Huang +4
As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cogni…
SentinelRAG: Synthetic Sentinel Knowledge for RAG Database Copyright Protection
Tsun On Kwok, Xi Yang, Ki Sen Hung +2
Protecting proprietary RAG databases from unauthorized redistribution is challenging: existing watermarking methods either inject fabricated relations between real entities, pollut…
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
Yuxuan Liu, Zhaochen Su, Lingyun Xie +11
Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures. Existing self-evolving methods refine skills using…
PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization
Huihao Jing, Wenbin Hu, Shaojin Chen +5
Large language models (LLMs) can often generate functionally correct code, but their ability to produce efficient implementations for performance-critical systems tasks remains lim…
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
Ki Sen Hung, Xi Yang, Chang Liu +7
A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. Th…
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
Wenbin Hu, Huihao Jing, Haochen Shi +3
Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data genera…
ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance
Haoran Li, Yulin Chen, Huihao Jing +6
Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context…
WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
Yulin Chen, Tri Cao, Haoran Li +7
Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accom…
Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards
Cheng Jiayang, Xin Liu, Zhihan Zhang +8
Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workfl…
Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
Yulin Chen, Haoran Li, Yuan Sui +2
With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-fo…
MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning
Huihao Jing, Wenbin Hu, Hongyu Luo +4
Multi-agent systems (MAS), leveraging the remarkable capabilities of Large Language Models (LLMs), show great potential in addressing complex tasks. In this context, integrating MA…
Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
Wenbin Hu, Huihao Jing, Haochen Shi +2
The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely o…
GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
Haoran Li, Jingru Zeng, Yulin Chen +8
As large language models (LLMs) are integrated into numerous applications, LLMs' safety becomes critical for both application developers and intended users. Currently, great effort…
TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
Yulin Chen, Haoran Li, Yuexin Li +3
Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish in…
XToM: Exploring the Multilingual Theory of Mind for Large Language Models
Chunkit Chan, Yauwai Yim, Hongchuan Zeng +14
Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in LLMs are largely limited to English, negle…
MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol
Huihao Jing, Haoran Li, Wenbin Hu +5
As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks. Its decentralized architecture, which separ…
Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
Wenbin Hu, Haoran Li, Huihao Jing +7
While Large Language Models (LLMs) exhibit remarkable capabilities, they also introduce significant safety and privacy risks. Current mitigation strategies often fail to preserve c…