CUEBES

A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning

arXiv:2601.21162v1 Announce Type: new Abstract: Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure....

Policy Biology

arXiv CS Jan 30

Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem Solving

arXiv:2601.21164v1 Announce Type: new Abstract: Plane Geometry Problem Solving (PGPS) is a multimodal reasoning task that aims to solve a plane geometric problem based on...

Software Energy

arXiv CS Jan 30

FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks

arXiv:2601.21165v1 Announce Type: new Abstract: We introduce FrontierScience, a benchmark evaluating expert-level scientific reasoning in frontier language models. Recent model progress has nearly saturated existing...

Physics Biology

arXiv CS Jan 30

Efficient Simple Regret Algorithms for Stochastic Contextual Bandits

arXiv:2601.21167v1 Announce Type: new Abstract: We study stochastic contextual logistic bandits under the simple regret objective. While simple regret guarantees have been established for the...

Software World News

arXiv CS Jan 30

Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space

arXiv:2601.21169v1 Announce Type: new Abstract: We introduce Output-Space Search (OS-Search), which turns LLM generation into endpoint search. An outer loop selects a target z* in...

Policy Software

arXiv CS Jan 30

The Powers of Precision: Structure-Informed Detection in Complex Systems -- From Customer Churn to Seizure Onset

arXiv:2601.21170v1 Announce Type: new Abstract: Emergent phenomena -- onset of epileptic seizures, sudden customer churn, or pandemic outbreaks -- often arise from hidden causal interactions...

Engineering Software

arXiv CS Jan 30

AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection

arXiv:2601.21171v1 Announce Type: new Abstract: Graph anomaly detection aims to identify abnormal patterns in networks, but faces significant challenges from label scarcity and extreme class...

Engineering Software

arXiv CS Jan 30

InspecSafe-V1: A Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios

arXiv:2601.21173v1 Announce Type: new Abstract: With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in complex...

Robotics Energy

arXiv CS Jan 30

Breaking the Reasoning Horizon in Entity Alignment Foundation Models

arXiv:2601.21174v1 Announce Type: new Abstract: Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning...

Biology Engineering

arXiv CS Jan 30

Towards Governance of Localized VANET: An Adjustable Degree Distribution Model

arXiv:2601.21176v1 Announce Type: new Abstract: Vehicular Ad-hoc Networks (VANETs) serve as a critical enabler for intelligent transportation systems. However, their practical deployment faces a core...

Policy Biology

arXiv CS Jan 30

Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling

arXiv:2601.21177v1 Announce Type: new Abstract: The scalability of continuous normalizing flows (CNFs) for unbiased Boltzmann sampling remains limited in high-dimensional systems due to the cost...

Mathematics Policy

arXiv CS Jan 30

Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process

arXiv:2601.21179v1 Announce Type: new Abstract: This work studies the challenging problem of acquiring high-quality underwater images via 4-D light field (LF) imaging. To this end,...

Software Energy

arXiv CS Jan 30

MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models

arXiv:2601.21181v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) suffer from cross-modal hallucinations, where one modality inappropriately influences generation about another, leading to fabricated...

Software Psychology

arXiv CS Jan 30

Rethinking Refinement: Correcting Generative Bias without Noise Injection

arXiv:2601.21182v1 Announce Type: new Abstract: Generative models, including diffusion and flow-based models, often exhibit systematic biases that degrade sample quality, particularly in high-dimensional settings. We...

Space & Astronomy Software

arXiv CS Jan 30

Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models

arXiv:2601.21183v1 Announce Type: new Abstract: Reasoning models frequently agree with incorrect user suggestions -- a behavior known as sycophancy. However, it is unclear where in...

Psychology Energy

arXiv CS Jan 30

From Logic to Toolchains: An Empirical Study of Bugs in the TypeScript Ecosystem

arXiv:2601.21186v1 Announce Type: new Abstract: TypeScript has rapidly become a popular language for modern web development, yet its effect on software faults remains poorly understood....

Biology Technology

arXiv CS Jan 30

FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models

arXiv:2601.21187v1 Announce Type: new Abstract: Efficiently enhancing the reasoning capabilities of Vision-Language Models (VLMs) by merging them with Large Reasoning Models (LRMs) has emerged as...

Software Policy

arXiv CS Jan 30

Disturbance-Aware Flight Control of Robotic Gliding Blimp via Moving Mass Actuation

arXiv:2601.21188v1 Announce Type: new Abstract: Robotic blimps, as lighter-than-air (LTA) aerial systems, offer long endurance and inherently safe operation but remain highly susceptible to wind...

Software Policy

arXiv CS Jan 30

Adaptive and Robust Cost-Aware Proof of Quality for Decentralized LLM Inference Networks

arXiv:2601.21189v1 Announce Type: new Abstract: Decentralized large language model inference networks require lightweight mechanisms to reward high quality outputs under heterogeneous latency and cost. Proof...

Policy Artificial Intelligence

arXiv CS Jan 30

From Linear Input to Hierarchical Structure: Function Words as Statistical Cues for Language Learning

arXiv:2601.21191v1 Announce Type: new Abstract: What statistical conditions support learning hierarchical structure from linear input? In this paper, we address this question by focusing on...

Neuroscience Engineering

arXiv CS Jan 30

Do Reasoning Models Enhance Embedding Models?

arXiv:2601.21192v1 Announce Type: new Abstract: State-of-the-art embedding models are increasingly derived from decoder-only Large Language Model (LLM) backbones adapted via contrastive learning. Given the emergence...

Psychology Software

arXiv CS Jan 30

Generative Recall, Dense Reranking: Learning Multi-View Semantic IDs for Efficient Text-to-Video Retrieval

arXiv:2601.21193v1 Announce Type: new Abstract: Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and...

Software Policy

arXiv CS Jan 30

Human-Agent versus Human Pull Requests: A Testing-Focused Characterization and Comparison

arXiv:2601.21194v1 Announce Type: new Abstract: AI-based coding agents are increasingly integrated into software development workflows, collaborating with developers to create pull requests (PRs). Despite their...

Software Technology

arXiv CS Jan 30

ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling

arXiv:2601.21198v1 Announce Type: new Abstract: While Mixture-of-Experts (MoE) architectures substantially bolster the expressive power of large-language models, their prohibitive memory footprint severely impedes the practical...

Psychology Technology