8 citations · 12 across the 30 of their papers we have counts for
20 papers · 1 filter
AgentMonopoly: Behavioral Patterns and Persona Control in LLM Agents
Changshun Wu, Mengyu Li, Mathis Marsault +2
How do LLM agents' strategies differ, and how much can instructions to adopt a persona change their behavior over a game? We study these questions with AgentMonopoly, an environmen…
Organising Trajectory Evidence for Language-Model Agent Assurance: Fragments, Methods, and the Residual
Xiaowei Huang
Methods for assessing language-model agents include rule checkers over logs, analyses of skill coverage and composition, support checkers, prefix monitors, execution gates, and rar…
Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts
Zhuoyun Li, Boxuan Wang, Xiaowei Huang +1
For multimodal large language models, when images or speech conflict with accompanying text, measured text reliance can entangle modality preference with evidence position. Earlier…
Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification
Yanni Dong, Minghua Liu, Meilin Zhu +2
Large Language Models often produce confidently stated yet unreliable outputs, posing critical challenges for deployment in safety-sensitive applications. Existing uncertainty metr…
Skill Use or Skill Theater? Evaluating the Reasoning Backroom in Skill-Augmented Language Agents
Jinwei Hu, Yi Qi, Xinmiao Huang +3
Reusable skills are becoming a standard interface for extending language agents with task procedures. Yet evaluators usually infer skill use from visible reasoning or the agent's o…
Skill Coverage: A Test Adequacy Metric for Agent Skills
Boyin Tan, Xiaowei Huang, Youcheng Sun
Agent skills encode reusable procedural knowledge for large language model (LLM) agents, and existing benchmarks show that such skills can improve task-level performance. However,…
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces
Jinwei Hu, Yi Dong, Youcheng Sun +1
Large Language Model (LLM)-based agents increasingly automate software engineering tasks through reusable skills, natural-language instruction documents that guide planning and exe…
SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings
Yingjie Wang, Yi Dong, Edmund Lau +3
Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets. Sub…
SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services
Zhuoyun Li, Boxuan Wang, Changshun Wu +2
Rejecting inputs outside the defined in-distribution (IND) service scope is critical for large language model (LLM) services, where unsupported requests should be filtered before f…
Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
Boxuan Wang, Zhuoyun Li, Xiaowei Huang +1
Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve intent while triggering common…
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
S. Bensalem, Y. Dong, M. Franzle +6
This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a st…
Responsible Agentic AI Requires Explicit Provenance
Jinwei Hu, Xinmiao Huang, Qisong He +3
Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reason is that responsibility, d…
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
Qisong He, Xinmiao Huang, Jinwei Hu +4
Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet most existing safe reinforc…
PrefixGuard: Online Failure Warning and Trace-Grounded Diagnosis for LLM Agents
Xinmiao Huang, Jinwei Hu, Rajarshi Roy +4
Large language model (LLM) agents execute multi-step tasks, but terminal verdicts arrive too late for intervention. Agent traces mix messages, tool calls, and feedback, making it d…
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
Zhuoyun Li, Boxuan Wang, Jinwei Hu +6
Large language models are sensitive to minor prompt perturbations, yet existing robustness methods usually enforce consistency at the whole-sequence level. This holistic view can h…
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
Qisong He, Jinwei Hu, Xinmiao Huang +3
In a long conversation, an LLM may produce a fluent continuation that rests on premises the conversation has already abandoned. Context-manipulation attacks exploit precisely this…
A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline
Mohamed Ahmed Mohamed, Xiaowei Huang
Object detection in adverse weather is critical for the safety of autonomous vehicles; however, the scarcity of labelled, real-world foggy data remains a significant bottleneck. In…
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
Zhuoyun Li, Boxuan Wang, Jinwei Hu +2
Robust adaptation of LLMs and VLMs is often evaluated by average accuracy or average consistency under perturbations. However, these averages can hide a structured failure mode: a…
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
Jinwei Hu, Shiyuan Meng, Yi Dong +1
Image transmission and processing systems in resource-critical applications face significant challenges from adversarial perturbations that compromise mission-specific object class…
Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
Jinwei Hu, Xinmiao Huang, Youcheng Sun +2
As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an unexpected attack surface. This paper…