arXiv:2602.03876v1 Announce Type: new
Abstract: Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing policy optimiza...
NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces
arXiv:2602.03901v1 Announce Type: new
Abstract: The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates ...
GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
arXiv:2602.03906v1 Announce Type: new
Abstract: Information Bottleneck (IB) is widely used, but in deep learning, it is usually implemented through tractable surrogates, such as variational bounds or neural mutual information (MI) estimators, rather than directly controlling the MI I(X;Z) itself. T...
Knowledge Model Prompting Increases LLM Performance on Planning Tasks
arXiv:2602.03900v1 Announce Type: new
Abstract: Large Language Models (LLM) can struggle with reasoning ability and planning tasks. Many prompting techniques have been developed to assist with LLM reasoning, notably Chain-of-Thought (CoT); however, these techniques, too, have come under scrutiny as...
Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning Augmentation
arXiv:2602.03950v1 Announce Type: new
Abstract: Mathematical problem solving is a fundamental benchmark for assessing the reasoning capabilities of artificial intelligence and a gateway to applications in education, science, and engineering where reliable symbolic reasoning is essential. Although r...
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
arXiv:2602.03955v1 Announce Type: new
Abstract: While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational cost and error propagation. This paper proposes AgentArk, a novel framewo...
Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical Structure
arXiv:2602.03975v1 Announce Type: new
Abstract: Test-time computation has become a primary driver of progress in large language model (LLM) reasoning, but it is increasingly bottlenecked by expensive verification. In many reasoning systems, a large fraction of verifier calls are spent on redundant ...
Augmenting Parameter-Efficient Pre-trained Language Models with Large Language Models
arXiv:2602.02501v1 Announce Type: new
Abstract: Training AI models in cybersecurity with help of vast datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models and the ris...
What Drives Length of Stay After Elective Spine Surgery? Insights from a Decade of Predictive Modeling
arXiv:2602.02517v1 Announce Type: new
Abstract: Objective: Predicting length of stay after elective spine surgery is essential for optimizing patient outcomes and hospital resource use. This systematic review synthesizes computational methods used to predict length of stay in this patient populatio...
CreditAudit: 2$^\text{nd}$ Dimension for LLM Evaluation and Selection
arXiv:2602.02515v2 Announce Type: new
Abstract: Leaderboard scores on public benchmarks have been steadily rising and converging, with many frontier language models now separated by only marginal differences. However, these scores often fail to match users' day to day experience, because system pro...
Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers
arXiv:2602.02559v1 Announce Type: new
Abstract: Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-intensive domains that demand long-horizon execution, tight coordination a...
Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems
arXiv:2602.02582v1 Announce Type: new
Abstract: Large language models (LLMs) enable powerful zero-shot recommendations by leveraging broad contextual knowledge, yet predictive uncertainty and embedded biases threaten reliability and fairness. This paper studies how uncertainty and fairness evaluati...
A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
arXiv:2602.02639v1 Announce Type: new
Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on identifyin...
OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models
arXiv:2602.00012v1 Announce Type: new
Abstract: We present OGD4All, a transparent, auditable, and reproducible framework based on Large Language Models (LLMs) to enhance citizens' interaction with geospatial Open Government Data (OGD). The system combines semantic data retrieval, agentic reasoning ...
Measurement for Opaque Systems: Multi-source Triangulation with Interpretable Machine Learning
arXiv:2602.00022v1 Announce Type: new
Abstract: We propose a measurement framework for difficult-to-access contexts that uses indirect data traces, interpretable machine-learning models, and theory-guided triangulation to fill inaccessible measurement spaces. Many high-stakes systems of scientific ...
ELLMPEG: An Edge-based Agentic LLM Video Processing Tool
arXiv:2602.00028v1 Announce Type: new
Abstract: Large language models (LLMs), the foundation of generative AI systems like ChatGPT, are transforming many fields and applications, including multimedia, enabling more advanced content generation, analysis, and interaction. However, cloud-based LLM dep...
RAPTOR-AI for Disaster OODA Loop: Hierarchical Multimodal RAG with Experience-Driven Agentic Decision-Making
arXiv:2602.00030v1 Announce Type: new
Abstract: Effective humanitarian assistance and disaster relief (HADR) requires rapid situational understanding, reliable decision support, and the ability to generalize across diverse and previously unseen disaster contexts. This work introduces an agentic Ret...
Scalable and Secure AI Inference in Healthcare: A Comparative Benchmarking of FastAPI and Triton Inference Server on Kubernetes
arXiv:2602.00053v1 Announce Type: new
Abstract: Efficient and scalable deployment of machine learning (ML) models is a prerequisite for modern production environments, particularly within regulated domains such as healthcare and pharmaceuticals. In these settings, systems must balance competing req...
Learning to Price: Interpretable Attribute-Level Models for Dynamic Markets
arXiv:2602.00188v1 Announce Type: new
Abstract: Dynamic pricing in high-dimensional markets poses fundamental challenges of scalability, uncertainty, and interpretability. Existing low-rank bandit formulations learn efficiently but rely on latent features that obscure how individual product attribu...
From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
arXiv:2602.00190v1 Announce Type: new
Abstract: Deep learning agents can achieve high performance in complex game domains without often understanding the underlying causal game mechanics. To address this, we investigate Causal Induction: the ability to infer governing laws from observational data, ...
Localizing and Correcting Errors for LLM-based Planners
arXiv:2602.00276v1 Announce Type: new
Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities on math and coding, but frequently fail on symbolic classical planning tasks. Our studies, as well as prior work, show that LLM-generated plans routinely violate domain const...
A Reinforcement Learning Based Universal Sequence Design for Polar Codes
To advance Polar code design for 6G applications, we develop a reinforcement learning-based universal sequence design framework that is extensible and adaptable to diverse channel conditions and decoding strategies. Crucially, our method scales to code lengths up to 2048, making it suitable for use ...
Attention Isn't All You Need for Emotion Recognition:Domain Features Outperform Transformers on the EAV Dataset
arXiv:2601.22161v1 Announce Type: new
Abstract: We present a systematic study of multimodal emotion recognition using the EAV dataset, investigating whether complex attention mechanisms improve performance on small datasets. We implement three model categories: baseline transformers (M1), novel fac...
Multitask Learning for Earth Observation Data Classification with Hybrid Quantum Network
arXiv:2601.22195v1 Announce Type: new
Abstract: Quantum machine learning (QML) has gained increasing attention as a potential solution to address the challenges of computation requirements in the future. Earth observation (EO) has entered the era of Big Data, and the computational demands for effec...