7 citations · 29 across the 54 of their papers we have counts for
55 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…
ZenGen: Social Mind for LLMs
ZenGen Team, Ao Xiang, Bi Jingping +57
As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track…
RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection
Shicheng Xu, Liang Pang, Liyi Chen +7
Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internalized Generation), a holistic…
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…
SelfEvoSkill: Paired Execution Audits for Skill Revision without External Outcome Supervision
Haowen Gao, Haoran Chen, Can Wang +5
Agent skills provide LLM agents with reusable procedures, but a given skill may be incomplete, ineffective, or misleading for the current task. Existing methods for revising skills…
ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning
Yunhan Jiang, Wenbin Duan, Shasha Guo +3
Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks. Existing memory mechanisms are largely centralized, typically organizing…
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…
Learning to Retrieve from Agent Trajectories
Yuqi Zhou, Sunhao Dai, Changle Qu +3
Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs…
DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage
Haowen Gao, Zhenyu Zhang, Liang Pang +7
Reinforcement learning (RL) with group relative policy optimization (GRPO) has become a widely adopted approach for enhancing the reasoning capabilities of multimodal large languag…
D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models
Jia Gu, Liang Pang, Huawei Shen +1
The predictive probability of the next token (P_token) in large language models (LLMs) is inextricably linked to the probability of relevance for the next piece of information, the…
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,…
ACE-Align: Attribute Causal Effect Alignment for Cultural Values under Varying Persona Granularities
Jiatang Luo, Bingbing Xu, Rongxin Chen +5
Ensuring that large language models (LLMs) reflect diverse cultural values is important for globally deployed NLP systems. However, existing approaches often treat cultural groups…
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…
GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation
Shasha Guo, Liang Pang, Xi Wang +3
Auxiliary lines are essential for solving complex geometric problems but remain challenging for large vision-language models (LVLMs). Recent attempts construct auxiliary lines via…
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…
Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model
Shicheng Xu, Xin Huang, Zihao Wei +3
Full-process clinical diagnosis in the real world encompasses the entire diagnostic workflow that begins with only an ambiguous chief complaint. While artificial intelligence (AI),…
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…
RLKD: Distilling LLMs' Reasoning via Reinforcement Learning
Shicheng Xu, Liang Pang, Yunchang Zhu +6
Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models…
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
Hanxing Ding, Shuchang Tao, Liang Pang +5
Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches fa…
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
Jingcheng Deng, Zhongtao Jiang, Liang Pang +5
A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently gen…
On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs
Hanxing Ding, Shuchang Tao, Liang Pang +5
Retrieval-augmented generation (RAG) systems traditionally employ sophisticated training strategies to enhance robustness against retrieval noise. In this work, we investigate a cr…