arXiv:2604.08293v1 Announce Type: cross Abstract: Software architecture documentation is essential for system comprehension, yet it is often unavailable or incomplete. While recent LLM-based techniques can generate documentation from code, they typically address local artifacts rather than producing coherent, system-level architectural descriptions. This paper presents a structured process for automatically generating system-level architectural documentation directly from […]
Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
arXiv:2604.08333v1 Announce Type: cross Abstract: The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However, as one of the earliest and most fundamental tasks integrated into this paradigm, medical image classification reveals a sobering reality: state-of-the-art medical MLLMs consistently underperform compared to […]
Phantasia: Context-Adaptive Backdoors in Vision Language Models
arXiv:2604.08395v1 Announce Type: cross Abstract: Recent advances in Vision-Language Models (VLMs) have greatly enhanced the integration of visual perception and linguistic reasoning, driving rapid progress in multimodal understanding. Despite these achievements, the security of VLMs, particularly their vulnerability to backdoor attacks, remains significantly underexplored. Existing backdoor attacks on VLMs are still in an early stage […]
Trust the AI, Doubt Yourself: The Effect of Urgency on Self-Confidence in Human-AI Interaction
arXiv:2604.07535v1 Announce Type: new Abstract: Studies show that interactions with an AI system fosters trust in human users towards AI. An often overlooked element of such interaction dynamics is the (sense of) urgency when the human user is prompted by an AI agent, e.g., for advice or guidance. In this paper, we show that although […]
Hybrid CNN-Transformer Architecture for Arabic Speech Emotion Recognition
arXiv:2604.07357v1 Announce Type: cross Abstract: Recognizing emotions from speech using machine learning has become an active research area due to its importance in building human-centered applications. However, while many studies have been conducted in English, German, and other European and Asian languages, research in Arabic remains scarce because of the limited availability of annotated datasets. […]
Are we still able to recognize pearls? Machine-driven peer review and the risk to creativity: An explainable RAG-XAI detection framework with markers extraction
arXiv:2604.07964v1 Announce Type: new Abstract: The integration of large language models (LLMs) into peer review raises a concern beyond authorship and detection: the potential cascading automation of the entire editorial process. As reviews become partially or fully machine-generated, it becomes plausible that editorial decisions may also be delegated to algorithmic systems, leading to a fully […]
Wiring the ‘Why’: A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
arXiv:2604.08016v1 Announce Type: new Abstract: Regardless of its foundational role in human discovery and sense-making, abductive reasoning–the inference of the most plausible explanation for an observation–has been relatively underexplored in Large Language Models (LLMs). Despite the rapid advancement of LLMs, the exploration of abductive reasoning and its diverse facets has thus far been disjointed rather […]
An Agentic Evaluation Architecture for Historical Bias Detection in Educational Textbooks
arXiv:2604.07883v1 Announce Type: new Abstract: History textbooks often contain implicit biases, nationalist framing, and selective omissions that are difficult to audit at scale. We propose an agentic evaluation architecture comprising a multimodal screening agent, a heterogeneous jury of five evaluative agents, and a meta-agent for verdict synthesis and human escalation. A central contribution is a […]
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
arXiv:2604.07922v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive “overthinking”, generating unnecessarily long reasoning chains. While current solutions improve token efficiency, they often sacrifice fine-grained control or risk disrupting the logical integrity of the reasoning process. To address this, we introduce Stepwise Adaptive Thinking (SAT), a […]
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
arXiv:2604.08401v1 Announce Type: new Abstract: In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing unsupported beliefs repeatedly stored and propagated across decision steps, leading to systematic behavioral drift in long-horizon agentic systems. Most […]
ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
arXiv:2604.08276v1 Announce Type: new Abstract: As generative artificial intelligence evolves, autonomous agent networks present a powerful paradigm for interactive covert communication. However, because agents dynamically update internal memories via environmental interactions, existing methods face a critical structural vulnerability: cognitive asymmetry. Conventional approaches demand strict cognitive symmetry, requiring identical sequence prefixes between the encoder and decoder. […]
Time-Varying Environmental and Polygenic Predictors of Substance Use Initiation in Youth: A Survival and Causal Modeling Study in the ABCD Cohort
arXiv:2604.07368v1 Announce Type: new Abstract: Early initiation of alcohol, nicotine, cannabis, and other substances predicts later substance use disorders and related psychopathology. We integrate time-varying environmental factors with polygenic risk scores (PRS) in a longitudinal framework to identify determinants of substance initiation in adolescence. Using data from the Adolescent Brain Cognitive Development (ABCD) Study with […]