📰 AI News

arXiv:2604.03058v1 Announce Type: cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather tha

arXiv:2604.03070v1 Announce Type: cross Abstract: Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in priv

arXiv:2604.03081v1 Announce Type: cross Abstract: LLM-based coding agents extend their capabilities via third-party agent skills distributed through open market

arXiv:2604.03094v1 Announce Type: cross Abstract: Accurate and automated sea ice classification is important for climate monitoring and maritime safety in the A

arXiv:2604.03098v1 Announce Type: cross Abstract: Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fu

arXiv:2604.03104v1 Announce Type: cross Abstract: Cyber-attacks continue to grow in scale and sophistication, yet existing network intrusion detection approache

arXiv:2604.03114v1 Announce Type: cross Abstract: VLMs trained on web-scale data retain sensitive and copyrighted visual concepts that deployment may require re

arXiv:2604.03121v1 Announce Type: cross Abstract: Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, b

arXiv:2604.03127v1 Announce Type: cross Abstract: Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient do

arXiv:2604.03131v1 Announce Type: cross Abstract: Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they al

arXiv:2604.03135v1 Announce Type: cross Abstract: Many software systems originate as prototypes or minimum viable products (MVPs), developed with an emphasis on

arXiv:2604.03144v1 Announce Type: cross Abstract: Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reason

arXiv:2604.03147v1 Announce Type: cross Abstract: We present a method to identify a valence-arousal (VA) subspace within large language model representations. F

arXiv:2604.03174v1 Announce Type: cross Abstract: Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally li

arXiv:2604.03179v1 Announce Type: cross Abstract: The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption

arXiv:2604.03189v1 Announce Type: cross Abstract: Generally capable agents must learn from experience in ways that generalize across tasks and environments. The

arXiv:2604.03190v1 Announce Type: cross Abstract: Transformer attention computes a single softmax-weighted average over values -- a one-pass estimate that canno

arXiv:2604.03192v1 Announce Type: cross Abstract: We study multiteacher knowledge distillation for low resource abstractive summarization from a reliability awa

arXiv:2604.03203v1 Announce Type: cross Abstract: Three-dimensional medical image data and computer-aided decision making, particularly using deep learning, are

arXiv:2604.03226v1 Announce Type: cross Abstract: This paper explores the use of server learning for enhancing the robustness of federated learning against mali

arXiv:2502.20689v3 Announce Type: replace Abstract: Large Language Models (LLMs) offer promising opportunities to support mental healthcare workflows, yet they

arXiv:2509.12643v4 Announce Type: replace Abstract: Large Language Model (LLM)-based optimization has recently shown promise for autonomous problem solving, yet

arXiv:2510.27176v5 Announce Type: replace Abstract: Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human

arXiv:2511.02734v2 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlook