arXiv:2601.18631v2 Announce Type: replace Abstract: When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning in multimodal large language models (MLLMs). Effective reasoning, therefore, hinges on knowing which tools to use, when to invoke them, and how to compose them over multiple steps, even when […]
Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models
arXiv:2503.02623v5 Announce Type: replace-cross Abstract: A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated confidence estimates alongside their answers to factual questions. Our method optimizes a reward based on […]
Spectral Representation-based Reinforcement Learning
arXiv:2512.15036v2 Announce Type: replace-cross Abstract: In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful approximations such as neural networks offer great expressiveness, they often present theoretical ambiguities, suffer from optimization instability and exploration difficulty, […]
Human Values in a Single Sentence: Moral Presence, Hierarchies, and Transformer Ensembles on the Schwartz Continuum
arXiv:2601.14172v2 Announce Type: replace-cross Abstract: We study sentence-level detection of the 19 human values in the refined Schwartz continuum in about 74k English sentences from news and political manifestos (ValueEval’24 corpus). Each sentence is annotated with value presence, yielding a binary moral-presence label and a 19-way multi-label task under severe class imbalance. First, we show […]
Exploring Transformer Placement in Variational Autoencoders for Tabular Data Generation
arXiv:2601.20854v1 Announce Type: cross Abstract: Tabular data remains a challenging domain for generative models. In particular, the standard Variational Autoencoder (VAE) architecture, typically composed of multilayer perceptrons, struggles to model relationships between features, especially when handling mixed data types. In contrast, Transformers, through their attention mechanism, are better suited for capturing complex feature interactions. In […]
AGFS-Tractometry: A Novel Atlas-Guided Fine-Scale Tractometry Approach for Enhanced Along-Tract Group Statistical Comparison Using Diffusion MRI Tractography
arXiv:2507.10601v2 Announce Type: replace Abstract: Diffusion MRI (dMRI) tractography is currently the only method for in vivo mapping of the brain’s white matter (WM) connections. Tractometry is an advanced tractography analysis technique for along-tract profiling to investigate the morphology and microstructural properties along the fiber tracts. Tractometry has become an essential tool for studying local […]
Cognition Envelopes for Bounded AI Reasoning in Autonomous UAS Operations
arXiv:2510.26905v2 Announce Type: replace Abstract: Cyber-physical systems increasingly rely on Foundational Models such as Large Language Models (LLMs) and Vision-Language Models (VLMs) to increase autonomy through enhanced perception, inference, and planning. However, these models also introduce new types of errors, such as hallucinations, overgeneralizations, and context misalignments, resulting in incorrect and flawed decisions. To address […]
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation
arXiv:2601.08430v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verification, existing methods suffer from scalability bottlenecks and coarse criteria, resulting in a supervision […]
LLM Multi-Agent Systems: Challenges and Open Problems
arXiv:2402.03578v3 Announce Type: replace-cross Abstract: This paper explores multi-agent systems and identify challenges that remain inadequately addressed. By leveraging the diverse capabilities and roles of individual agents, multi-agent systems can tackle complex tasks through agent collaboration. We discuss optimizing task allocation, fostering robust reasoning through iterative debates, managing complex and layered context information, and enhancing […]
MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
arXiv:2502.11068v2 Announce Type: replace-cross Abstract: Anchors is a popular local model-agnostic explanation technique whose applicability is limited by its computational inefficiency. To address this limitation, we propose a memorization-based framework that accelerates Anchors while preserving explanation fidelity and interpretability. Our approach leverages the iterative nature of Anchors’ algorithm which gradually refines an explanation until it […]
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
arXiv:2504.19373v4 Announce Type: replace-cross Abstract: Recent advances in multi-modal large reasoning models (MLRMs) have shown significant ability to interpret complex visual content. While these models enable impressive reasoning capabilities, they also introduce novel and underexplored privacy risks. In this paper, we identify a novel category of privacy leakage in MLRMs: Adversaries can infer sensitive geolocation […]
HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
arXiv:2506.07972v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have demonstrated significant advancements in reasoning and agent-based problem-solving, current evaluation methodologies fail to adequately assess their capabilities: existing benchmarks either rely on closed-ended questions prone to saturation and memorization, or subjective comparisons that lack consistency and rigor. In this work, we introduce HeuriGym, an […]