LLM Router: Prefill is All You Need
arXiv:2603.20895v1 Announce Type: new Abstract: LLMs often share comparable benchmark accuracies, but their complementary performance across task subsets suggests that an Oracle router--a theoretical selector with perfect foresight--can significantly surpass standalone model accuracy by navigating model-specific strengths. While current routers...
Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent Representations
arXiv:2603.20327v1 Announce Type: new Abstract: Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the visual verification pathway of generative models, creating...
Interpretable Multiple Myeloma Prognosis with Observational Medical Outcomes Partnership Data
arXiv:2603.20341v1 Announce Type: new Abstract: Machine learning (ML) promises better clinical decision-making, yet opaque model behavior limits the adoption in healthcare. We propose two novel regularization techniques for ensuring the interpretability of ML models trained on real-world data. In particular,...
Delightful Distributed Policy Gradient
arXiv:2603.20521v1 Announce Type: new Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log-probability) under the learner's policy. The core difficulty is not surprising data per se, but \emph{negative learning...
LJ-Bench: Ontology-Based Benchmark for U.S. Crime
arXiv:2603.20572v1 Announce Type: new Abstract: The potential of Large Language Models (LLMs) to provide harmful information remains a significant concern due to the vast breadth of illegal queries they may encounter. Unfortunately, existing benchmarks only focus on a handful types...
Exponential Family Discriminant Analysis: Generalizing LDA-Style Generative Classification to Non-Gaussian Models
arXiv:2603.20655v1 Announce Type: new Abstract: We introduce Exponential Family Discriminant Analysis (EFDA), a unified generative framework that extends classical Linear Discriminant Analysis (LDA) beyond the Gaussian setting to any member of the exponential family. Under the assumption that each class-conditional...
Large Neighborhood Search meets Iterative Neural Constraint Heuristics
arXiv:2603.20801v1 Announce Type: new Abstract: Neural networks are being increasingly used as heuristics for constraint satisfaction. These neural methods are often recurrent, learning to iteratively refine candidate assignments. In this work, we make explicit the connection between such iterative neural...
Court reverses ruling on qualified immunity, denies review of death-row case and First Amendment challenge by citizen journalist
In a list of orders released on Monday morning, the Supreme Court reversed a ruling by a federal appeals court, holding that a Vermont police officer is entitled to qualified […]The postCourt reverses ruling on qualified immunity, denies review of...
Birthright citizenship: reading the text and sidestepping the parent trap
“The text is the law, and it is the text that must be observed,” Justice Antonin Scalia famously insisted at page 22 of a notable book on legal interpretation. “Only […]The postBirthright citizenship: reading the text and sidestepping the parent...
Grounded Multimodal Retrieval-Augmented Drafting of Radiology Impressions Using Case-Based Similarity Search
arXiv:2603.17765v1 Announce Type: cross Abstract: Automated radiology report generation has gained increasing attention with the rise of deep learning and large language models. However, fully generative approaches often suffer from hallucinations and lack clinical grounding, limiting their reliability in real-world...
Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams
arXiv:2603.19250v1 Announce Type: new Abstract: Evaluating language models in streaming environments is critical, yet underexplored. Existing benchmarks either focus on single complex events or provide curated inputs for each query, and do not evaluate models under the conflicts that arise...
Reviewing the Reviewer: Graph-Enhanced LLMs for E-commerce Appeal Adjudication
arXiv:2603.19267v1 Announce Type: new Abstract: Hierarchical review workflows, where a second-tier reviewer (Checker) corrects first-tier (Maker) decisions, generate valuable correction signals that encode why initial judgments failed. However, learning from these signals is hindered by information asymmetry: corrections often depend...
Autonoma: A Hierarchical Multi-Agent Framework for End-to-End Workflow Automation
arXiv:2603.19270v1 Announce Type: new Abstract: The increasing complexity of user demands necessitates automation frameworks that can reliably translate open-ended instructions into robust, multi-step workflows. Current monolithic agent architectures often struggle with the challenges of scalability, error propagation, and maintaining focus...
PrefPO: Pairwise Preference Prompt Optimization
arXiv:2603.19311v1 Announce Type: new Abstract: Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO, a minimal prompt optimization approach inspired by...
CLaRE-ty Amid Chaos: Quantifying Representational Entanglement to Predict Ripple Effects in LLM Editing
arXiv:2603.19297v1 Announce Type: new Abstract: The static knowledge representations of large language models (LLMs) inevitably become outdated or incorrect over time. While model-editing techniques offer a promising solution by modifying a model's factual associations, they often produce unpredictable ripple effects,...
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
arXiv:2603.19312v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision...
Heavy-Tailed and Long-Range Dependent Noise in Stochastic Approximation: A Finite-Time Analysis
arXiv:2603.19648v1 Announce Type: new Abstract: Stochastic approximation (SA) is a fundamental iterative framework with broad applications in reinforcement learning and optimization. Classical analyses typically rely on martingale difference or Markov noise with bounded second moments, but many practical settings, including...
Unanimous court allows street preacher’s free speech case to move forward
A unanimous court on Friday sided with a Mississippi street preacher who sued to block future enforcement of a public demonstration ordinance that he was previously convicted of violating. A […]The postUnanimous court allows street preacher’s free speech case to...
Oral argument live blog for Wednesday, April 1
On Wednesday, April 1, we will be live blogging as the court hears argument in Trump v. Barbara, on the constitutionality of President Donald Trump’s executive order on birthright citizenship. […]The postOral argument live blog for Wednesday, April 1appeared first...
New court filing reveals Pentagon told Anthropic the two sides were nearly aligned — a week after Trump declared the relationship kaput
Anthropic submitted two sworn declarations to a California federal court late Friday afternoon, pushing back on the Pentagon's assertion that the AI company poses an "unacceptable risk to national security" and arguing that the government's case relies on technical misunderstandings...
Retrieval-Augmented LLM Agents: Learning to Learn from Experience
arXiv:2603.18272v1 Announce Type: new Abstract: While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current approaches typically rely on either fine-tuning or training-free memory-augmented generation using retrieved...
The Validity Gap in Health AI Evaluation: A Cross-Sectional Analysis of Benchmark Composition
arXiv:2603.18294v1 Announce Type: new Abstract: Background: Clinical trials rely on transparent inclusion criteria to ensure generalizability. In contrast, benchmarks validating health-related large language models (LLMs) rarely characterize the "patient" or "query" populations they contain. Without defined composition, aggregate performance metrics...
Agentic Framework for Political Biography Extraction
arXiv:2603.18010v1 Announce Type: new Abstract: The production of large-scale political datasets typically demands extracting structured facts from vast piles of unstructured documents or web sources, a task that traditionally relies on expensive human experts and remains prohibitively difficult to automate...
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
arXiv:2603.18718v1 Announce Type: new Abstract: Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled challenges: strategic blindness on the forward path of...
AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba
arXiv:2603.18462v1 Announce Type: new Abstract: In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While Transformer-based methods have excelled at modeling inter-modal dependencies,...
Consumer-to-Clinical Language Shifts in Ambient AI Draft Notes and Clinician-Finalized Documentation: A Multi-level Analysis
arXiv:2603.18327v1 Announce Type: new Abstract: Ambient AI generates draft clinical notes from patient-clinician conversations, often using lay or consumer-oriented phrasing to support patient understanding instead of standardized clinical terminology. How clinicians revise these drafts for professional documentation conventions remains unclear....
Analysis Of Linguistic Stereotypes in Single and Multi-Agent Generative AI Architectures
arXiv:2603.18729v1 Announce Type: new Abstract: Many works in the literature show that LLM outputs exhibit discriminatory behaviour, triggering stereotype-based inferences based on the dialect in which the inputs are written. This bias has been shown to be particularly pronounced when...
How Psychological Learning Paradigms Shaped and Constrained Artificial Intelligence
arXiv:2603.18203v1 Announce Type: new Abstract: The dominant paradigms of artificial intelligence were shaped by learning theories from psychology: behaviorism inspired reinforcement learning, cognitivism gave rise to deep learning and memory-augmented architectures, and constructivism influenced curriculum learning and compositional approaches. This...
Engineering Verifiable Modularity in Transformers via Per-Layer Supervision
arXiv:2603.18029v1 Announce Type: new Abstract: Transformers resist surgical control. Ablating an attention head identified as critical for capitalization produces minimal behavioral change because distributed redundancy compensates for damage. This Hydra effect renders interpretability illusory: we may identify components through correlation,...
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
arXiv:2603.18113v1 Announce Type: new Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objective in trustworthy AI. This challenge becomes even more pronounced when...