CUEBES

Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation

arXiv:2601.21464v1 Announce Type: new Abstract: Training large language models (LLMs) for non-verifiable tasks, such as creative writing, dialogue, and ethical reasoning, remains challenging due to...

Policy Biology

arXiv CS Jan 30

Topeax -- An Improved Clustering Topic Model with Density Peak Detection and Lexical-Semantic Term Importance

arXiv:2601.21465v1 Announce Type: new Abstract: Text clustering is today the most popular paradigm for topic modelling, both in academia and industry. Despite clustering topic models'...

Software Business

arXiv CS Jan 30

A block-coordinate descent framework for non-convex composite optimization. Application to sparse precision matrix estimation

arXiv:2601.21467v1 Announce Type: new Abstract: Block-coordinate descent (BCD) is the method of choice to solve numerous large scale optimization problems, however their theoretical study for...

Software Biology

arXiv CS Jan 30

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning

arXiv:2601.21468v1 Announce Type: new Abstract: Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history...

Energy Policy

arXiv CS Jan 30

Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation

arXiv:2601.21469v1 Announce Type: new Abstract: While Large Language Models (LLMs) have catalyzed breakthroughs in automated code generation, Small Language Models (SLMs) often encounter reasoning bottlenecks...

Software Technology

arXiv CS Jan 30

PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization

arXiv:2601.21470v1 Announce Type: new Abstract: We study semi-supervised stochastic optimization when labeled data is scarce but predictions from pre-trained models are available. PPI and SVRG...

Energy Mathematics

arXiv CS Jan 30

Best Arm Identification with LLM Judges and Limited Human

arXiv:2601.21471v1 Announce Type: new Abstract: We study fixed-confidence best-arm identification (BAI) where a cheap but potentially biased proxy (e.g., LLM judge) is available for every...

Artificial Intelligence Mathematics

arXiv CS Jan 30

ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management

arXiv:2601.21473v1 Announce Type: new Abstract: LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each...

Software Policy

arXiv CS Jan 30

DexTac: Learning Contact-aware Visuotactile Policies via Hand-by-hand Teaching

arXiv:2601.21474v1 Announce Type: new Abstract: For contact-intensive tasks, the ability to generate policies that produce comprehensive tactile-aware motions is essential. However, existing data collection and...

Policy Robotics

arXiv CS Jan 30

Task-free Adaptive Meta Black-box Optimization

arXiv:2601.21475v1 Announce Type: new Abstract: Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure...

Software Biology

arXiv CS Jan 30

SOUP: Token-level Single-sample Mix-policy Reinforcement Learning for Large Language Models

arXiv:2601.21476v1 Announce Type: new Abstract: On-policy reinforcement learning (RL) methods widely used for language model post-training, like Group Relative Policy Optimization (GRPO), often suffer from...

Policy Software

arXiv CS Jan 30

Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions

arXiv:2601.21477v1 Announce Type: new Abstract: Mean-field control (MFC) offers a scalable solution to the curse of dimensionality in multi-agent systems but traditionally hinges on the...

Policy Artificial Intelligence

arXiv CS Jan 30

Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking

arXiv:2601.21479v1 Announce Type: new Abstract: In this paper, we present the first attempt to estimate the necessity of debulking coronary artery calcifications from computed tomography...

Health Software

arXiv CS Jan 30

Learning-Based Sensor Scheduling for Delay-Aware and Stable Remote State Estimation

arXiv:2601.21482v1 Announce Type: new Abstract: Unpredictable sensor-to-estimator delays fundamentally distort what matters for wireless remote state estimation: not just freshness, but how delay interacts with...

Energy Policy

arXiv CS Jan 30

DimStance: Multilingual Datasets for Dimensional Stance Analysis

arXiv:2601.21483v1 Announce Type: new Abstract: Stance detection is an established task that classifies an author's attitude toward a specific target into categories such as Favor,...

Psychology Environment

arXiv CS Jan 30

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment

arXiv:2601.21484v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training alignment for language models is effective, but also costly and unstable in practice, owing to its...

Energy Policy

arXiv CS Jan 30

HADUA: Hierarchical Attention and Dynamic Uniform Alignment for Robust Cross-Subject Emotion Recognition

arXiv:2601.21488v1 Announce Type: new Abstract: Robust cross-subject emotion recognition from multimodal physiological signals remains a challenging problem, primarily due to modality heterogeneity and inter-subject distribution...

Psychology Software

arXiv CS Jan 30

Are they just delegating? Cross-Sample Predictions on University Students' & Teachers' Use of AI

arXiv:2601.21490v1 Announce Type: new Abstract: Mutual trust between teachers and students is a prerequisite for effective teaching, learning, and assessment in higher education. Accurate predictions...

Artificial Intelligence Psychology

arXiv CS Jan 30

Organizational Practices and Socio-Technical Design of Human-Centered AI

arXiv:2601.21492v1 Announce Type: new Abstract: This contribution explores how the integration of Artificial Intelligence (AI) into organizational practices can be effectively framed through a socio-technical...

Artificial Intelligence Technology

arXiv CS Jan 30

The Path of Least Resistance: Guiding LLM Reasining Trajectories with Prefix Consensus

arXiv:2601.21494v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance, but inference strategies such as Self-Consistency (SC) are computationally expensive, as they fully...

Software Policy

arXiv CS Jan 30

SimGraph: A Unified Framework for Scene Graph-Based Image Generation and Editing

arXiv:2601.21498v1 Announce Type: new Abstract: Recent advancements in Generative Artificial Intelligence (GenAI) have significantly enhanced the capabilities of both image generation and editing. However, current...

Software Energy

arXiv CS Jan 30

Task-Awareness Improves LLM Generations and Uncertainty

arXiv:2601.21500v1 Announce Type: new Abstract: In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values,...

Software Engineering

arXiv CS Jan 30

MAR: Efficient Large Language Models via Module-aware Architecture Refinement

arXiv:2601.21503v1 Announce Type: new Abstract: Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense...

Neuroscience Artificial Intelligence

arXiv CS Jan 30

Don't double it: Efficient Agent Prediction in Occlusions

arXiv:2601.21504v1 Announce Type: new Abstract: Occluded traffic agents pose a significant challenge for autonomous vehicles, as hidden pedestrians or vehicles can appear unexpectedly, yet this...

Robotics Software