214 citations · 1.5k across the 43 of their papers we have counts for
48 papers
Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
Saiyue Lyu, Jerrold Huang, Yunbei Zhang +4
Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We i…
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Jerrold Huang, Junwei Quan, Saiyue Lyu +2
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical…
VERSE: Verified Self-Evolving Optimizer for Agent Harnesses
Zekai Wang, Yingqiang Ge, Zekun Wang +6
Harness evolution improves an LLM agent's prompts, tools, and workflow, while the optimizer's own tools and procedures often remain fixed. We study whether an optimizer can improve…
Safety Must Survive Self-Improvement: Why Failures Persist and How Agents Recover
Yunbei Zhang, Janet Wang, Saiyue Lyu +5
Recursive self-improvement (RSI) allows agents to carry useful changes across generations. Maintaining safety across these generations involves both preventing unsafe behavior from…
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
Yunbei Zhang, Saiyue Lyu, Janet Wang +4
Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contribut…
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
Xi Fang, Weijie Xu, Yingqiang Ge +3
Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response. Modern LLMs personalize interactions by…
One Skill, Two Masters: Serving Users and Attackers through Skill Injection
Haochang Hao, Dehai Min, Zhifang Zhang +5
Large language model agents use skills that package reusable instructions, code, and resources. Existing skill-injection attacks exploit trust in these packages by adding malicious…
Stop Comparing LLM Agents Without Disclosing the Harness
Yunbei Zhang, Janet Wang, Yingqiang Ge +3
This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer th…
ClawSafety: "Safe" LLMs, Unsafe Agents
Bowen Wei, Yunbei Zhang, Jinhao Pan +5
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transact…
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
Haochang Hao, Yifan Xu, Xinzhuo Li +2
Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which rec…
Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook
Yunbei Zhang, Kai Mei, Ming Liu +5
We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580 comments over 9 days. We report thre…
Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
Yunbei Zhang, Yingqiang Ge, Weijie Xu +3
Current multimodal red teaming treats images as wrappers for malicious payloads via typography or adversarial noise. These attacks are structurally brittle, as standard defenses ne…
The 1st Workshop on Human-Centered Recommender Systems
Kaike Zhang, Yunfan Wu, Yougang lyu +6
Recommender systems are quintessential applications of human-computer interaction. Widely utilized in daily life, they offer significant convenience but also present numerous chall…
IDGenRec: LLM-RecSys Alignment with Textual ID Learning
Juntao Tan, Shuyuan Xu, Wenyue Hua +3
Generative recommendation based on Large Language Models (LLMs) have transformed the traditional ranking-based recommendation style into a text-to-text generation paradigm. However…
AIOS: LLM Agent Operating System
Kai Mei, Xi Zhu, Wujiang Xu +7
LLM-based intelligent agents face significant deployment challenges, particularly related to resource management. Allowing unrestricted access to LLM or tool resources can lead to…
PAP-REC: Personalized Automatic Prompt for Recommendation Language Model
Zelong Li, Jianchao Ji, Yingqiang Ge +2
Recently emerged prompt-based Recommendation Language Models (RLM) can solve multiple recommendation tasks uniformly. The RLMs make full use of the inherited knowledge learned from…
LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem
Yingqiang Ge, Yujie Ren, Wenyue Hua +3
This paper envisions a revolutionary AIOS-Agent ecosystem, where Large Language Model (LLM) serves as the (Artificial) Intelligent Operating System (IOS, or AIOS)--an operating sys…
War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
Wenyue Hua, Lizhou Fan, Lingyao Li +5
Can we avoid wars at the crossroads of history? This question has been pursued by individuals, scholars, policymakers, and organizations throughout human history. In this research,…
User-Controllable Recommendation via Counterfactual Retrospective and Prospective Explanations
Juntao Tan, Yingqiang Ge, Yan Zhu +4
Modern recommender systems utilize users' historical behaviors to generate personalized recommendations. However, these systems often lack user controllability, leading to diminish…
GenRec: Large Language Model for Generative Recommendation
Jianchao Ji, Zelong Li, Shuyuan Xu +4
In recent years, large language models (LLM) have emerged as powerful tools for diverse natural language processing tasks. However, their potential for recommender systems under th…
Counterfactual Collaborative Reasoning
Jianchao Ji, Zelong Li, Shuyuan Xu +5
Causal reasoning and logical reasoning are two important types of reasoning abilities for human intelligence. However, their relationship has not been extensively explored under ma…
Automated Data Denoising for Recommendation
Yingqiang Ge, Mostafa Rahmani, Athirai Irissappane +3
In real-world scenarios, most platforms collect both large-scale, naturally noisy implicit feedback and small-scale yet highly relevant explicit feedback. Due to the issue of data…
UP5: Unbiased Foundation Model for Fairness-aware Recommendation
Wenyue Hua, Yingqiang Ge, Shuyuan Xu +2
Recent advances in Foundation Models such as Large Language Models (LLMs) have propelled them to the forefront of Recommender Systems (RS). Despite their utility, there is a growin…
How to Index Item IDs for Recommendation Foundation Models
Wenyue Hua, Shuyuan Xu, Yingqiang Ge +1
Recommendation foundation model utilizes large language models (LLM) for recommendation by converting recommendation tasks into natural language tasks. It enables generative recomm…