22 papers
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
Houcheng Jiang, Boxuan Zhang, Qiyong Zhong +3
Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware safeguards mainly rely on promp…
EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models
Jie Sun, Mao Zheng, Mingyang Song +7
Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillat…
Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation
Miaomiao Cai, Yunshan Ma, Fangqi Zhu +5
Multi-behavior recommendation improves target-behavior prediction by exploiting heterogeneous auxiliary feedback (e.g., view, collect, and cart), yet its robustness is undermined b…
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
Zhepei Hong, Lin Wang, Liting Li +5
Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level o…
SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
Jie Sun, Mao Zheng, Mingyang Song +6
On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparabl…
Rubric-based On-policy Distillation
Junfeng Fang, Zhepei Hong, Mao Zheng +7
On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that struct…
SOD: Step-wise On-policy Distillation for Small Language Model Agents
Qiyong Zhong, Mao Zheng, Mingyang Song +5
Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While reinforcement…
A Systematic Security Evaluation of OpenClaw and Its Variants
Yuhang Wang, Haichang Gao, Zhenxing Niu +4
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-on…
DRAFT: Task Decoupled Latent Reasoning for Agent Safety
Lin Wang, Junfeng Fang, Dan Zhang +3
The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making…
Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
Jinghan Li, Junfeng Fang, Jinda Lu +5
Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models.…
NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
Junfeng Fang, Nachuan Chen, Houcheng Jiang +5
Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time…
3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
Chang Wu, Zhiyuan Liu, Wen Shu +6
Masked graph modeling (MGM) is a promising approach for molecular representation learning (MRL).However, extending the success of re-mask decoding from 2D to 3D MGM is non-trivial,…
Contrastive Weak-to-strong Generalization
Houcheng Jiang, Junfeng Fang, Jiaxin Wu +5
Weak-to-strong generalization provides a promising paradigm for scaling large language models (LLMs) by training stronger models on samples from aligned weaker ones, without requir…
We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
Junfeng Fang, Zijun Yao, Ruipeng Wang +3
The development of large language models (LLMs) has entered in a experience-driven era, flagged by the emergence of environment feedback-driven learning via reinforcement learning…
DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation
Houcheng Jiang, Zetong Zhao, Junfeng Fang +5
Safety-aligned large language models (LLMs) remain vulnerable to backdoor attacks. Recent model editing-based approaches enable efficient backdoor injection by directly modifying a…
SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
Junfeng Fang, Yukai Wang, Ruipeng Wang +5
The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutio…
ACE: Concept Editing in Diffusion Models without Performance Degradation
Ruipeng Wang, Junfeng Fang, Jiaqi Li +4
Diffusion-based text-to-image models have demonstrated remarkable capabilities in generating realistic images, but they raise societal and ethical concerns, such as the creation of…
Reinforced Lifelong Editing for Language Models
Zherui Li, Houcheng Jiang, Hao Chen +5
Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this cha…
AnyEdit: Edit Any Knowledge Encoded in Language Models
Houcheng Jiang, Junfeng Fang, Ningyu Zhang +5
Large language models (LLMs) often produce incorrect or outdated information, necessitating efficient and precise knowledge updates. Current model editing methods, however, struggl…
Multi-agent Architecture Search via Agentic Supernet
Guibin Zhang, Luyang Niu, Junfeng Fang +3
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing…
Neuron-Level Sequential Editing for Large Language Models
Houcheng Jiang, Junfeng Fang, Tianyu Zhang +4
This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round…
Text-guided Diffusion Model for 3D Molecule Generation
Yanchen Luo, Junfeng Fang, Sihang Li +5
The de novo generation of molecules with targeted properties is crucial in biology, chemistry, and drug discovery. Current generative models are limited to using single property va…