ExpGuard: LLM Content Moderation in Specialized Domains
arXiv:2603.02588v1 Announce Type: new Abstract: With the growing deployment of large language models (LLMs) in real-world applications, establishing robust safety guardrails to moderate their inputs and outputs has become essential to ensure adherence to safety policies. Current guardrail models predominantly...
Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
arXiv:2603.03565v1 Announce Type: new Abstract: Conversational shopping assistants (CSAs) represent a compelling application of agentic AI, but moving from prototype to production reveals two underexplored challenges: how to evaluate multi-turn interactions and how to optimize tightly coupled multi-agent systems. Grocery...
Evaluating the Search Agent in a Parallel World
arXiv:2603.04751v1 Announce Type: new Abstract: Integrating web search tools has significantly extended the capability of LLMs to address open-world, real-time, and long-tail problems. However, evaluating these Search Agents presents formidable challenges. First, constructing high-quality deep search benchmarks is prohibitively expensive,...
Rethinking Representativeness and Diversity in Dynamic Data Selection
arXiv:2603.04981v1 Announce Type: new Abstract: Dynamic data selection accelerates training by sampling a changing subset of the dataset while preserving accuracy. We rethink two core notions underlying sample evaluation: representativeness and diversity. Instead of local geometric centrality, we define representativeness...
AegisUI: Behavioral Anomaly Detection for Structured User Interface Protocols in AI Agent Systems
arXiv:2603.05031v1 Announce Type: new Abstract: AI agents that build user interfaces on the fly assembling buttons, forms, and data displays from structured protocol payloads are becoming common in production systems. The trouble is that a payload can pass every schema...
FedEMA-Distill: Exponential Moving Average Guided Knowledge Distillation for Robust Federated Learning
arXiv:2603.04422v1 Announce Type: new Abstract: Federated learning (FL) often degrades when clients hold heterogeneous non-Independent and Identically Distributed (non-IID) data and when some clients behave adversarially, leading to client drift, slow convergence, and high communication overhead. This paper proposes FedEMA-Distill,...
Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation
arXiv:2603.04478v1 Announce Type: new Abstract: Pretraining for electroencephalogram (EEG) foundation models has predominantly relied on self-supervised masked reconstruction, a paradigm largely adapted from and inspired by the success of vision and language foundation models. However, unlike images and text, EEG...
Invariant Causal Routing for Governing Social Norms in Online Market Economies
arXiv:2603.04534v1 Announce Type: new Abstract: Social norms are stable behavioral patterns that emerge endogenously within economic systems through repeated interactions among agents. In online market economies, such norms -- like fair exposure, sustained participation, and balanced reinvestment -- are critical...
FedAFD: Multimodal Federated Learning via Adversarial Fusion and Distillation
arXiv:2603.04890v1 Announce Type: new Abstract: Multimodal Federated Learning (MFL) enables clients with heterogeneous data modalities to collaboratively train models without sharing raw data, offering a privacy-preserving framework that leverages complementary cross-modal information. However, existing methods often overlook personalized client performance...
EVMbench: Evaluating AI Agents on Smart Contract Security
arXiv:2603.04915v1 Announce Type: new Abstract: Smart contracts on public blockchains now manage large amounts of value, and vulnerabilities in these systems can lead to substantial losses. As AI agents become more capable at reading, writing, and running code, it is...
The Untold Story of the Proto-Smith Era: Justice O’Connor’s Papers and the Court’s Free Exercise Revolution
Justice O’Connor’s recently released Supreme Court papers reveal the untold story of how the Court systematically dismantled religious accommodation protections in the decade leading up to Employment Division v. Smith. While Smith’s abandonment of strict scrutiny for neutral, generally applicable...
SCOTUStoday for Friday, March 6
On this day in 1857, the Supreme Court released its opinion in Dred Scott v. Sandford, holding that Scott, an enslaved man who spent time in free territory, was not […]The postSCOTUStoday for Friday, March 6appeared first onSCOTUSblog.
Fine-Tuning and Evaluating Conversational AI for Agricultural Advisory
arXiv:2603.03294v1 Announce Type: cross Abstract: Large Language Models show promise for agricultural advisory, yet vanilla models exhibit unsupported recommendations, generic advice lacking specific, actionable detail, and communication styles misaligned with smallholder farmer needs. In high stakes agricultural contexts, where recommendation...
Developing an AI Assistant for Knowledge Management and Workforce Training in State DOTs
arXiv:2603.03302v1 Announce Type: cross Abstract: Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based instruction, and informal mentorship, often lead to fragmented...
Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
arXiv:2603.03314v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable and steadily improving performance across a wide range of tasks. However, LLM performance may be highly sensitive to prompt variations especially in scenarios with limited openness or strict...
M-QUEST -- Meme Question-Understanding Evaluation on Semantics and Toxicity
arXiv:2603.03315v1 Announce Type: cross Abstract: Internet memes are a powerful form of online communication, yet their nature and reliance on commonsense knowledge make toxicity detection challenging. Identifying key features for meme interpretation and understanding, is a crucial task. Previous work...
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
arXiv:2603.03378v1 Announce Type: new Abstract: Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execution under permission-governed...
Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
arXiv:2603.03530v1 Announce Type: new Abstract: Frozen self-supervised representations often transfer well with only a few labels across many semantic tasks. We argue that a single geometric quantity, \emph{directional} CDNV (decision-axis variance), sits at the core of two favorable behaviors: strong...
Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
arXiv:2603.03725v1 Announce Type: new Abstract: The volume of freely scraped data on the Internet has driven the tremendous success of deep learning. Along with this comes the growing concern about data privacy and security. Numerous methods for generating unlearnable examples...
PRISM: Exploring Heterogeneous Pretrained EEG Foundation Model Transfer to Clinical Differential Diagnosis
arXiv:2603.02268v1 Announce Type: new Abstract: EEG foundation models are typically pretrained on narrow-source clinical archives and evaluated on benchmarks from the same ecosystem, leaving unclear whether representations encode neural physiology or recording-distribution artifacts. We introduce PRISM (Population Representative Invariant Signal...
The Malignant Tail: Spectral Segregation of Label Noise in Over-Parameterized Networks
arXiv:2603.02293v1 Announce Type: new Abstract: While implicit regularization facilitates benign overfitting in low-noise regimes, recent theoretical work predicts a sharp phase transition to harmful overfitting as the noise-to-signal ratio increases. We experimentally isolate the geometric mechanism of this transition: the...
Thermodynamic Regulation of Finite-Time Gibbs Training in Energy-Based Models: A Restricted Boltzmann Machine Study
arXiv:2603.02525v1 Announce Type: new Abstract: Restricted Boltzmann Machines (RBMs) are typically trained using finite-length Gibbs chains under a fixed sampling temperature. This practice implicitly assumes that the stochastic regime remains valid as the energy landscape evolves during learning. We argue...
Opinions for Wednesday, March 4
We were live as the court released its opinions in Urias-Orellana v. Bondi and Galette v. New Jersey Transit Corp..The postOpinions for Wednesday, March 4appeared first onSCOTUSblog.
The US military is still using Claude — but defense-tech clients are fleeing
As the U.S. continues its aerial attack on Iran, Anthropic models are being used for many targeting decisions.
Conformal Prediction for Risk-Controlled Medical Entity Extraction Across Clinical Domains
arXiv:2603.00924v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for medical entity extraction, yet their confidence scores are often miscalibrated, limiting safe deployment in clinical settings. We present a conformal prediction framework that provides finite-sample coverage guarantees...
CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
arXiv:2603.00039v1 Announce Type: new Abstract: LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw: they implicitly assume that judges provide independent estimates of true quality. However, in practice, LLM judges exhibit...
Property-Driven Evaluation of GNN Expressiveness at Scale: Datasets, Framework, and Study
arXiv:2603.00044v1 Announce Type: new Abstract: Advancing trustworthy AI requires principled software engineering approaches to model evaluation. Graph Neural Networks (GNNs) have achieved remarkable success in processing graph-structured data, however, their expressiveness in capturing fundamental graph properties remains an open challenge....
BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning
arXiv:2603.00049v1 Announce Type: new Abstract: Self-Supervised Learning (SSL) has shifted from pixel-level reconstruction to latent space prediction, spearheaded by the Joint Embedding Predictive Architecture (JEPA). While effective, standard JEPA models typically rely on a uni-directional prediction mechanism (e.g. Context $\to$...
Engineering FAIR Privacy-preserving Applications that Learn Histories of Disease
arXiv:2603.00181v1 Announce Type: new Abstract: A recent report on "Learning the natural history of human disease with generative transformers" created an opportunity to assess the engineering challenge of delivering user-facing Generative AI applications in privacy-sensitive domains. The application of these...
FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments
arXiv:2602.23504v1 Announce Type: new Abstract: Federated Learning (FL) enables a group of clients to collaboratively train a model without sharing individual data, but its performance drops when client data are heterogeneous. Clustered FL tackles this by grouping similar clients. However,...