arXiv:2604.20043v1 Announce Type: cross Abstract: Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present textbfTriEx, a tri-view explainability framework that instruments sequential decision making with aligned artifacts: (i) structured first-person self-reasoning bound to an action, (ii) explicit second-person […]
Prism: An Evolutionary Memory Substrate for Multi-Agent Open-Ended Discovery
arXiv:2604.19795v1 Announce Type: new Abstract: We introduce prism (textbfProbabilistic textbfRetrieval with textbfInformation-textbfStratified textbfMemory), an evolutionary memory substrate for multi-agent AI systems engaged in open-ended discovery. prism unifies four independently developed paradigms — layered file-based persistence, vector-augmented semantic memory, graph-structured relational memory, and multi-agent evolutionary search — under a single decision-theoretic framework with eight interconnected subsystems. […]
Meta Additive Model: Interpretable Sparse Learning With Auto Weighting
arXiv:2604.20111v1 Announce Type: cross Abstract: Sparse additive models have attracted much attention in high-dimensional data analysis due to their flexible representation and strong interpretability. However, most existing models are limited to single-level learning under the mean-squared error criterion, whose empirical performance can degrade significantly in the presence of complex noise, such as non-Gaussian perturbations, outliers, […]
Analyzing Shapley Additive Explanations to Understand Anomaly Detection Algorithm Behaviors and Their Complementarity
arXiv:2602.00208v2 Announce Type: replace-cross Abstract: Unsupervised anomaly detection is a challenging problem due to the diversity of data distributions and the lack of labels. Ensemble methods are often adopted to mitigate these challenges by combining multiple detectors, which can reduce individual biases and increase robustness. Yet building an ensemble that is genuinely complementary remains challenging, […]
IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
arXiv:2604.20136v1 Announce Type: cross Abstract: Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection, forcing annotators to revisit raw video and reconstruct temporal logic from scratch. The core bottleneck is not generation quality alone, but the absence of a supervisory interface through […]
The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms
arXiv:2604.19803v1 Announce Type: new Abstract: Agentic AI is rapidly transforming the way research is conducted, from prototyping ideas to reproducing results found in the literature. In this paper, we explore the ability of agentic AI to autonomously design wireless communication algorithms. To that end, we implement a dedicated framework that leverages large language models (LLMs) […]
From Scene to Object: Text-Guided Dual-Gaze Prediction
arXiv:2604.20191v1 Announce Type: cross Abstract: Interpretable driver attention prediction is crucial for human-like autonomous driving. However, existing datasets provide only scene-level global gaze rather than fine-grained object-level annotations, inherently failing to support text-grounded cognitive modeling. Consequently, while Vision-Language Models (VLMs) hold great potential for semantic reasoning, this critical data limitations leads to severe text-vision decoupling […]
Degrees, Levels, and Profiles of Contextuality
arXiv:2603.26692v3 Announce Type: replace-cross Abstract: We introduce a new notion, that of a contextuality profile of a system of random variables. Rather than characterizing a system’s contextuality by a single number, its overall degree of contextuality, we show how it can be characterized by a curve relating degree of contextuality to level at which the […]
Hybrid Policy Distillation for LLMs
arXiv:2604.20244v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of existing KD methods and present a unified view that establishes connections between them, reformulating KD as a […]
Modeling of Pneumococcal and Respiratory Syncytial Virus Pneumonia: An Epidemiological Review, with Statistical Inference
arXiv:2604.19805v1 Announce Type: new Abstract: Infectious diseases continue to pose significant public health challenges worldwide, requiring effective prevention and control strategies to mitigate their negative impact. Infectious diseases can be broadly classified into two groups: vaccine-preventable diseases (e.g., measles, polio, influenza, hepatitis B, pneumonia) and vaccine-non-preventable diseases (e.g., HIV/AIDS). Vaccine-preventable disease models are one of […]
Text Steganography with Dynamic Codebook and Multimodal Large Language Model
arXiv:2604.20269v1 Announce Type: cross Abstract: With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance. However, existing methods still have some issues: (1) For the white-box paradigm, this steganography behavior is prone to exposure due to sharing the off-the-shelf language model between Alice and Bob.(2) For the black-box paradigm, these […]
Mechanistic Decoding of Cognitive Constructs in Large Language Models
arXiv:2604.14593v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving the cognitive structure of more complex affective states underexplored. To bridge this gap, […]