4 citations · 8 across the 13 of their papers we have counts for
14 papers
SkillAtlas: An Attack Trace Library for Agent Skills
Yuxin Tian, Zenghao Duan, Liang Pang +2
Agent skills are reusable units for language-model agents, but their risks emerge through model decisions, user context, tool calls, and execution feedback rather than through stab…
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models
Zihao Wei, Wenjie Shi, Liang Pang +8
Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often continue generating unnecessary reasoning after a correct answer has emerged. We…
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Jingcheng Deng, Zihao Wei, Liang Pang +4
Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reason…
SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
Zenghao Duan, Yuxin Tian, Zhiyi Yin +6
LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to t…
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
Zenghao Duan, Zhiyi Yin, Zhichao Shi +8
Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g.…
Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models
Zenghao Duan, Liang Pang, Zihao Wei +6
Despite the success of test-time scaling, Large Reasoning Models (LRMs) frequently encounter repetitive loops that lead to computational waste and inference failure. In this paper,…
LLM Latent Reasoning as Chain of Superposition
Jingcheng Deng, Liang Pang, Zihao Wei +6
Latent reasoning offers a computation-efficient alternative to Chain-of-Thought but often suffers from performance degradation due to distributional misalignment and ambiguous chai…
A Survey of Vibe Coding with Large Language Models
Yuyao Ge, Lingrui Mei, Zenghao Duan +12
The advancement of large language models (LLMs) has catalyzed a paradigm shift from code generation assistance to autonomous coding agents, enabling a novel development methodology…
Large Language Model Sourcing: A Survey
Liang Pang, Jia Gu, Sunhao Dai +7
Due to the black-box nature of large language models (LLMs) and the realism of their generated content, issues such as hallucinations, bias, unfairness, and copyright infringement…
Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs
Yu Yan, Sheng Sun, Zhe Wang +6
With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in…
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
Zihao Wei, Liang Pang, Jiahao Liu +7
Test-time scaling via explicit reasoning trajectories significantly boosts large language model (LLM) performance but often triggers overthinking. To explore this, we analyze reaso…
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace
Zenghao Duan, Zhiyi Yin, Zhichao Shi +6
This paper investigates the underlying mechanisms of toxicity generation in Large Language Models (LLMs) and proposes an effective detoxification approach. Prior work typically con…
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
Yu Yan, Sheng Sun, Zenghao Duan +5
Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful…
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
Zenghao Duan, Wenbin Duan, Zhiyi Yin +5
Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject…