Enhancing Safety of Large Language Models via Embedding Space Separation
arXiv:2603.20206v1 Announce Type: new Abstract: Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe queries in LLMs...
FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems
arXiv:2603.20252v1 Announce Type: new Abstract: As organizations increasingly integrate AI-powered question-answering systems into financial information systems for compliance, risk assessment, and decision support, ensuring the factual accuracy of AI-generated outputs becomes a critical engineering challenge. Current Knowledge Graph (KG)-augmented QA...
A Framework for Low-Latency, LLM-driven Multimodal Interaction on the Pepper Robot
arXiv:2603.21013v1 Announce Type: new Abstract: Despite recent advances in integrating Large Language Models (LLMs) into social robotics, two weaknesses persist. First, existing implementations on platforms like Pepper often rely on cascaded Speech-to-Text (STT)->LLM->Text-to-Speech (TTS) pipelines, resulting in high latency and...
Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions
arXiv:2603.20925v1 Announce Type: new Abstract: As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by adversaries,...
NeurIPS Datasets & Benchmarks Track: From Art to Science in AI Evaluations
Weber's Law in Transformer Magnitude Representations: Efficient Coding, Representational Geometry, and Psychophysical Laws in Language Models
arXiv:2603.20642v1 Announce Type: new Abstract: How do transformer language models represent magnitude? Recent work disagrees: some find logarithmic spacing, others linear encoding, others per-digit circular representations. We apply the formal tools of psychophysics to resolve this. Using four converging paradigms...
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...
A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
arXiv:2603.19685v1 Announce Type: new Abstract: Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic content and long sequences of actions,...
Stepwise: Neuro-Symbolic Proof Search for Automated Systems Verification
arXiv:2603.19715v1 Announce Type: new Abstract: Formal verification via interactive theorem proving is increasingly used to ensure the correctness of critical systems, yet constructing large proof scripts remains highly manual and limits scalability. Advances in large language models (LLMs), especially in...
Improving Automatic Summarization of Radiology Reports through Mid-Training of Large Language Models
arXiv:2603.19275v1 Announce Type: cross Abstract: Automatic summarization of radiology reports is an essential application to reduce the burden on physicians. Previous studies have widely used the "pre-training, fine-tuning" strategy to adapt large language models (LLMs) for summarization. This study proposed...
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...
Scalable Prompt Routing via Fine-Grained Latent Task Discovery
arXiv:2603.19415v1 Announce Type: new Abstract: Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow...
FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment
arXiv:2603.19539v1 Announce Type: new Abstract: We introduce an expert curated, real-world benchmark for evaluating document-grounded question-answering (QA) motivated by generic drug assessment, using the U.S. Food and Drug Administration (FDA) drug label documents. Drug labels contain rich but heterogeneous clinical...
Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers
arXiv:2603.19544v1 Announce Type: new Abstract: Artificial Intelligence for scientific applications increasingly requires training large models on data that cannot be centralized due to privacy constraints, data sovereignty, or the sheer volume of data generated. Federated learning (FL) addresses this by...
Wearable Foundation Models Should Go Beyond Static Encoders
arXiv:2603.19564v1 Announce Type: new Abstract: Wearable foundation models (WFMs), trained on large volumes of data collected by affordable, always-on devices, have demonstrated strong performance on short-term, well-defined health monitoring tasks, including activity recognition, fitness tracking, and cardiovascular signal assessment. However,...
Scale-Dependent Radial Geometry and Metric Mismatch in Wasserstein Propagation for Reverse Diffusion
arXiv:2603.19670v1 Announce Type: new Abstract: Existing analyses of reverse diffusion often propagate sampling error in the Euclidean geometry underlying \(\Wtwo\) along the entire reverse trajectory. Under weak log-concavity, however, Gaussian smoothing can create contraction first at large separations while short...
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,...
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...
Balanced Thinking: Improving Chain of Thought Training in Vision Language Models
arXiv:2603.18656v1 Announce Type: new Abstract: Multimodal reasoning in vision-language models (VLMs) typically relies on a two-stage process: supervised fine-tuning (SFT) and reinforcement learning (RL). In standard SFT, all tokens contribute equally to the loss, even though reasoning data are inherently...
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...
Beyond Passive Aggregation: Active Auditing and Topology-Aware Defense in Decentralized Federated Learning
arXiv:2603.18538v1 Announce Type: new Abstract: Decentralized Federated Learning (DFL) remains highly vulnerable to adaptive backdoor attacks designed to bypass traditional passive defense metrics. To address this limitation, we shift the defensive paradigm toward a novel active, interventional auditing framework. First,...
Personalized Fall Detection by Balancing Data with Selective Feedback Using Contrastive Learning
arXiv:2603.17148v1 Announce Type: new Abstract: Personalized fall detection models can significantly improve accuracy by adapting to individual motion patterns, yet their effectiveness is often limited by the scarcity of real-world fall data and the dominance of non-fall feedback samples. This...
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
arXiv:2603.17187v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and...
Optimizing Hospital Capacity During Pandemics: A Dual-Component Framework for Strategic Patient Relocation
arXiv:2603.15960v1 Announce Type: new Abstract: The COVID-19 pandemic has placed immense strain on hospital systems worldwide, leading to critical capacity challenges. This research proposes a two-part framework to optimize hospital capacity through patient relocation strategies. The first component involves developing...
AsgardBench - Evaluating Visually Grounded Interactive Planning Under Minimal Feedback
arXiv:2603.15888v1 Announce Type: new Abstract: With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation during execution based on visual observations rather than navigation or low-level manipulation. In the landscape...
POLAR:A Per-User Association Test in Embedding Space
arXiv:2603.15950v1 Announce Type: new Abstract: Most intrinsic association probes operate at the word, sentence, or corpus level, obscuring author-level variation. We present POLAR (Per-user On-axis Lexical Association Re-port), a per-user lexical association test that runs in the embedding space of...
Quantum-Secure-By-Construction (QSC): A Paradigm Shift For Post-Quantum Agentic Intelligence
arXiv:2603.15668v1 Announce Type: new Abstract: As agentic artificial intelligence systems scale across globally distributed and long lived infrastructures, secure and policy compliant communication becomes a fundamental systems challenge. This challenge grows more serious in the quantum era, where the cryptographic...
An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc
arXiv:2603.15976v1 Announce Type: new Abstract: While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional benchmarks reduce evaluation to test-case matching, an approach insufficient for library code in HPC where...
RadAnnotate: Large Language Models for Efficient and Reliable Radiology Report Annotation
arXiv:2603.16002v1 Announce Type: new Abstract: Radiology report annotation is essential for clinical NLP, yet manual labeling is slow and costly. We present RadAnnotate, an LLM-based framework that studies retrieval-augmented synthetic reports and confidence-based selective automation to reduce expert effort for...