11 citations · 18 across the 22 of their papers we have counts for
24 papers
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
Zhijie Zheng, Yu Li, Chen Qian +5
LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modification, information leakage,…
MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insights
Yilun Liu, Miao Zhang, Shimin Tao +9
Multilingual and multicultural benchmarks now cover dozens of languages and model families, but the resulting score landscapes remain metric-rich and insight-poor, necessitating fi…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
Rover: Context-aware Conflict Resolution with LLM
Qingyu Zhang, Junzhe Li, Jiayi Lin +2
Code merging is a significant challenge, particularly in large-scale projects. Existing solutions, including program analysis and machine learning, show promise but face critical l…
On the Blessing of Pre-training in Weak-to-Strong Generalization
Wei Yao, Wang Zhaoyang, Gengze Xu +5
The paradigm of Weak-to-Strong Generalization (W2SG) suggests that a pre-trained strong model can surpass its weak supervisor, yet the decisive role of pre-training remains theoret…
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
Junyao Yang, Chen Qian, Kun Wang +4
The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-step ``slow thinking'' reason…
Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning
Ziqi Miao, Haonan Jia, Lijun Li +4
Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR appr…
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Zhaopeng Feng, Liangcai Su, Zhen Zhang +16
As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing cont…
Interpreting Emergent Extreme Events in Multi-Agent Systems
Ling Tang, Jilin Mei, Dongrui Liu +4
Large language model-powered multi-agent systems have emerged as powerful tools for simulating complex human-like systems. The interactions within these systems often lead to extre…
The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
Chen Qian, Peng Wang, Dongrui Liu +10
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more…
ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
Junyao Yang, Chen Qian, Dongrui Liu +3
Large Reasoning Models (LRMs) with long chain-of-thought reasoning have recently achieved remarkable success. Yet, equipping domain-specialized models with such reasoning capabilit…
Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
Yuan Xiong, Ziqi Miao, Lijun Li +3
While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus o…
Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm
Dadi Guo, Tianyi Zhou, Dongrui Liu +8
Recent advances in large language models (LLMs) and agent system designs have empowered agents with unprecedented levels of capability. However, existing agent benchmarks are showi…
Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
Guanxu Chen, Yafu Li, Yuxian Jiang +6
Reinforcement Learning with Verifiable Rewards (RLVR) for large language models (LLMs) has achieved remarkable progress in enhancing LLMs' reasoning capabilities on tasks with clea…
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
Shuai Shao, Qihan Ren, Chen Qian +8
Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the environment, demonstrating strong c…
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Lab, :, Yicheng Bao +115
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…
Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Chen Qian, Dongrui Liu, Haochen Wen +3
Large reasoning models (LRMs) have demonstrated impressive capabilities in complex problem-solving, yet their internal reasoning mechanisms remain poorly understood. In this paper,…
LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
Qianli Ma, Dongrui Liu, Qian Chen +2
Fine-tuning pre-trained Large Language Models (LLMs) for specialized tasks incurs substantial computational and data costs. While model merging offers a training-free solution to i…
Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
Yunkai Dang, Kaichen Huang, Jiahao Huo +11
The rapid development of Artificial Intelligence (AI) has revolutionized numerous fields, with large language models (LLMs) and computer vision (CV) systems driving advancements in…
REEF: Representation Encoding Fingerprints for Large Language Models
Jie Zhang, Dongrui Liu, Chen Qian +4
Protecting the intellectual property of open-source Large Language Models (LLMs) is very important, because training LLMs costs extensive computational resources and data. Therefor…
The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models
Chen Qian, Dongrui Liu, Jie Zhang +2
Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's…
The Better Angels of Machine Personality: How Personality Relates to LLM Safety
Jie Zhang, Dongrui Liu, Chen Qian +4
Personality psychologists have analyzed the relationship between personality and safety behaviors in human society. Although Large Language Models (LLMs) demonstrate personality tr…
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
Chen Qian, Jie Zhang, Wei Yao +5
Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness.…
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
Chaochao Lu, Chen Qian, Guodong Zheng +33
Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents. However, there is still a wide ga…