Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment
arXiv:2604.03867v1 Announce Type: new Abstract: Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However, existing methods...
TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables
arXiv:2604.03660v1 Announce Type: new Abstract: Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance remains limited for complex tables with...
Don't Blink: Evidence Collapse during Multimodal Reasoning
arXiv:2604.04207v1 Announce Type: new Abstract: Reasoning VLMs can become more accurate while progressively losing visual grounding as they think. This creates task-conditional danger zones where low-entropy predictions are confident but ungrounded, a failure mode text-only monitoring cannot detect. Evaluating three...
Compliance-by-Construction Argument Graphs: Using Generative AI to Produce Evidence-Linked Formal Arguments for Certification-Grade Accountability
arXiv:2604.04103v1 Announce Type: new Abstract: High-stakes decision systems increasingly require structured justification, traceability, and auditability to ensure accountability and regulatory compliance. Formal arguments commonly used in the certification of safety-critical systems provide a mechanism for structuring claims, reasoning, and evidence...
Neural Operators for Multi-Task Control and Adaptation
arXiv:2604.03449v1 Announce Type: new Abstract: Neural operator methods have emerged as powerful tools for learning mappings between infinite-dimensional function spaces, yet their potential in optimal control remains largely unexplored. We focus on multi-task control problems, whose solution is a mapping...
When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling
arXiv:2604.03562v1 Announce Type: new Abstract: Adaptive reward design for deep reinforcement learning (DRL) in multi-beam LEO satellite scheduling is motivated by the intuition that regime-aware reward weights should outperform static ones. We systematically test this intuition and uncover a switching-stability...
Understanding When Poisson Log-Normal Models Outperform Penalized Poisson Regression for Microbiome Count Data
arXiv:2604.03853v1 Announce Type: new Abstract: Multivariate count models are often justified by their ability to capture latent dependence, but researchers receive little guidance on when this added structure improves on simpler penalized marginal Poisson regression. We study this question using...
Evaluating Artificial Intelligence Through a Christian Understanding of Human Flourishing
arXiv:2604.03356v1 Announce Type: new Abstract: Artificial intelligence (AI) alignment is fundamentally a formation problem, not only a safety problem. As Large Language Models (LLMs) increasingly mediate moral deliberation and spiritual inquiry, they do more than provide information; they function as...
CODE-GEN: A Human-in-the-Loop RAG-Based Agentic AI System for Multiple-Choice Question Generation
arXiv:2604.03926v1 Announce Type: new Abstract: We present CODE-GEN, a human-in-the-Loop, retrieval-augmented generation (RAG)-based agentic AI system for generating context-aligned multiple-choice questions to develop student code reasoning and comprehension abilities. CODE-GEN employs an agentic AI architecture in which a Generator agent...
Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graphs from Complex Documents
arXiv:2604.03496v1 Announce Type: new Abstract: Knowledge graph construction typically relies either on predefined ontologies or on schema-free extraction. Ontology-driven pipelines enforce consistent typing but require costly schema design and maintenance, whereas schema-free methods often produce fragmented graphs with weak global...
Position: Science of AI Evaluation Requires Item-level Benchmark Data
arXiv:2604.03244v1 Announce Type: new Abstract: AI evaluations have become the primary evidence for deploying generative AI systems across high-stakes domains. However, current evaluation paradigms often exhibit systemic validity failures. These issues, ranging from unjustified design choices to misaligned metrics, remain...
FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
arXiv:2604.03893v1 Announce Type: new Abstract: Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus on local information...
Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors
arXiv:2604.03631v1 Announce Type: new Abstract: On-screen learning behavior provides valuable insights into how students seek, use, and create information during learning. Analyzing on-screen behavioral engagement is essential for capturing students' cognitive and collaborative processes. The recent development of Vision Language...
Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
arXiv:2604.03911v1 Announce Type: new Abstract: Generating molecular dynamics (MD) trajectories using deep generative models has attracted increasing attention, yet remains inherently challenging due to the limited availability of MD data and the complexities involved in modeling high-dimensional MD distributions. To...
Automated Conjecture Resolution with Formal Verification
arXiv:2604.03789v1 Announce Type: new Abstract: Recent advances in large language models have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving to increasingly capable performance on research-level problems. However, reliably solving and verifying such problems remains...
Beyond Retrieval: Modeling Confidence Decay and Deterministic Agentic Platforms in Generative Engine Optimization
arXiv:2604.03656v1 Announce Type: new Abstract: Generative Engine Optimization (GEO) is rapidly reshaping digital marketing paradigms in the era of Large Language Models (LLMs). However, current GEO strategies predominantly rely on Retrieval-Augmented Generation (RAG), which inherently suffers from probabilistic hallucinations and...
What really happens on the emergency docket
By now, readers of SCOTUSblog are quite familiar with the Supreme Court’s emergency docket, where parties come to the court seeking emergency orders, oftentimes without full briefing and oral argument. […]The postWhat really happens on the emergency docketappeared first onSCOTUSblog.
Towards the AI Historian: Agentic Information Extraction from Primary Sources
arXiv:2604.03553v1 Announce Type: new Abstract: AI is supporting, accelerating, and automating scientific discovery across a diverse set of fields. However, AI adoption in historical research remains limited due to the lack of solutions designed for historians. In this technical progress...
MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification
arXiv:2604.03586v1 Announce Type: new Abstract: With the growing prevalence of multimodal news content, effective news topic classification demands models capable of jointly understanding and reasoning over heterogeneous data such as text and images. Existing methods often process modalities independently or...
InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories
arXiv:2604.04106v1 Announce Type: new Abstract: The generation of realistic and controllable GPS trajectories is a fundamental task for applications in urban planning, mobility simulation, and privacy-preserving data sharing. However, existing methods face a two-fold challenge: they lack the deep semantic...
A Model of Understanding in Deep Learning Systems
arXiv:2604.04171v1 Announce Type: new Abstract: I propose a model of systematic understanding, suitable for machine learning systems. On this account, an agent understands a property of a target system when it contains an adequate internal model that tracks real regularities,...
Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models
arXiv:2604.04204v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, yet they expose only limited language settings, most notably "English (US)," despite the global diversity and colonial history of English. Through a postcolonial framing to...
DRAFT: Task Decoupled Latent Reasoning for Agent Safety
arXiv:2604.03242v1 Announce Type: new Abstract: The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit assignment. To address this, we...
Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus
arXiv:2604.03809v1 Announce Type: new Abstract: Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majority vote, implicitly assuming that agents contribute complementary evidence. We embed each agent's chain-of-thought rationale and measure pairwise similarity: across...
IC3-Evolve: Proof-/Witness-Gated Offline LLM-Driven Heuristic Evolution for IC3 Hardware Model Checking
arXiv:2604.03232v1 Announce Type: new Abstract: IC3, also known as property-directed reachability (PDR), is a commonly-used algorithm for hardware safety model checking. It checks if a state transition system complies with a given safety property. IC3 either returns UNSAFE (indicating property...
Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison
arXiv:2604.04064v1 Announce Type: new Abstract: Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whether they possess the internal emotion representations recently discovered in frontier models remains unknown. We present the first comparative analysis of...
From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities
arXiv:2604.03920v1 Announce Type: new Abstract: LLM-based social simulations can generate believable community interactions, enabling ``policy wind tunnels'' where governance interventions are tested before deployment. But believability is not causality. Claims like ``intervention $A$ reduces escalation'' require causal semantics that current...
Automated Attention Pattern Discovery at Scale in Large Language Models
arXiv:2604.03764v1 Announce Type: new Abstract: Large language models have found success by scaling up capabilities to work in general settings. The same can unfortunately not be said for interpretability methods. The current trend in mechanistic interpretability is to provide precise...
'Layer su Layer': Identifying and Disambiguating the Italian NPN Construction in BERT's family
arXiv:2604.03673v1 Announce Type: new Abstract: Interpretability research has highlighted the importance of evaluating Pretrained Language Models (PLMs) and in particular contextual embeddings against explicit linguistic theories to determine what linguistic information they encode. This study focuses on the Italian NPN...
Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems
arXiv:2604.02668v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit sycophancy: agreement with user stance even when it conflicts with the model's opinion. While prior work has mostly studied this in single-agent settings, it remains underexplored in collaborative multi-agent...