arXiv:2605. 23243v2 Announce Type: replace-cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five production-style applications with 118 ground-truth vulnerabilities across 20+ CWE families, which we will open-source).
By Vivek Dahiya, Sunny Nehra, Vipul Dholariya, Bhavik Shangari, Chandra Khatri
arXiv:2602. 06547v4 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.
By Yi Liu, Zhihao Chen, Yanjun Zhang, Gelei Deng, Yuekang Li, Jianting Ning, Leo Yu Zhang
arXiv:2606. 11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts.
By Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu, Zhewei Yao, Yuxiong He
arXiv:2606. 11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution.
By Yuqi Zhang, Di Zhang
arXiv:2601. 04710v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation.
By Feihu Jin, Shipeng Cen, Ying Tan
arXiv:2606. 11543v1 Announce Type: new Abstract: Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized.
By Zhiyu Chen, Zihan Guo, Bo Huang, Bingwei Lu, Jianghao Lin, Yuanjian Zhou, Weinan Zhang
arXiv:2606. 11205v1 Announce Type: cross Abstract: Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements.
By Matthew James Buchan
arXiv:2601. 17717v3 Announce Type: replace Abstract: Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities.
By Kaituo Zhang, Mingzhi Hu, Hoang Anh Duy Le, Fariha Kabir Torsha, Zhimeng Jiang, Minh Khai Bui, Chia-Yuan Chang, Yu-Neng Chuang, Zhen Xiong, Ying Lin, Guanchu Wang, Na Zou
arXiv:2606. 11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single "personalization" capability: given a user's history, is the output more user-aware?
By Youwang Deng
arXiv:2606. 11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes.
By Derek Yohn, Luke Flancher, Mirajul Islam, Khaled Slhoub
arXiv:2602. 22962v2 Announce Type: replace Abstract: Data-driven models are revolutionizing weather forecasting.
By Yuejiang Yu, Langwen Huang, Alexandru Calotoiu, Torsten Hoefler
arXiv:2606. 11688v1 Announce Type: cross Abstract: Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified.
By Youwang Deng
arXiv:2606. 11625v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) are increasingly explored as predictive experts within emerging agentic time-series systems.
By Kanghui Ning, Yushan Jiang, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka, Dongjin Song
arXiv:2606. 11652v1 Announce Type: new Abstract: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents.
By Yifan Yang, Zhen Zhang, Jiayi Tian, Liyan Tan, Zheng Zhang
arXiv:2606. 11860v1 Announce Type: new Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT).
By Christoph Koller, Johannes F\"urnkranz, Timo Bertram
arXiv:2606. 11868v1 Announce Type: new Abstract: De novo peptide sequencing from tandem mass spectrometry is pivotal in proteomics, enabling identification of novel peptides without reference databases.
By Dongxin Lyu, Jingbo Zhou, Hongxin Xiang, Yuqiang Li, Jun Xia
arXiv:2606. 11961v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as conditional generators for structured data, relying on in-context learning (ICL) to adapt to new distributions without parameter updates.
By Antonio Pelusi, Stefano Braghin, Alberto Trombetta
arXiv:2606. 12332v1 Announce Type: cross Abstract: Evaluating multi-turn dialogue is challenging because quality emerges across turns rather than within individual responses.
By Paul He, Shiva Kasiviswanathan, Dominik Janzing
arXiv:2506. 20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure.
By Ankur Garg, Xuemin Yu, Hassan Sajjad, Samira Ebrahimi Kahou
arXiv:2510. 03520v2 Announce Type: replace-cross Abstract: Ensuring safety is a foundational requirement for large language models (LLMs).
By Kartik Pandit, Sourav Ganguly, Arnesh Banerjee, Shaahin Angizi, Arnob Ghosh