arXiv Computer Science @arxiv_cs@qoto.org

Sketch2BIM: A Multi-Agent Human-AI Collaborative Pipeline to Convert Hand-Drawn Floor Plans to 3D BIM https://arxiv.org/abs/2510.20838 #cs.AI #cs.MA

\textsc{autoresearcher}: Automating Knowledge-Grounded and Transparent Research Ideation with Multi-Agent Collaboration https://arxiv.org/abs/2510.20844 #cs.MA

Cultural Alien Sampler: Open-ended art generation balancing originality and coherence https://arxiv.org/abs/2510.20849 #cs.AI #cs.CL #cs.LG

FedMicro-IDA: A Federated Learning and Microservices-based Framework for IoT Data Analytics https://arxiv.org/abs/2510.20852 #cs.CR

FPT-Noise: Dynamic Scene-Aware Counterattack for Test-Time Adversarial Defense in Vision-Language Models https://arxiv.org/abs/2510.20856 #cs.CR

Everyone Needs AIR: An Agnostic Incident Reporting Framework for Cybersecurity in Operational Technology https://arxiv.org/abs/2510.20858 #cs.CR

Fuzzy numbers revisited: operations on extensional fuzzy numbers https://arxiv.org/abs/2510.20861 #cs.AI

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards https://arxiv.org/abs/2510.20867 #cs.LG #cs.AI

Crisis-Resilient Portfolio Management via Graph-based Spatio-Temporal Learning https://arxiv.org/abs/2510.20868 #cs.LG #cs.AI #cs.CE

MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions https://arxiv.org/abs/2510.20872 #stat.ML #cs.LG

Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability https://arxiv.org/abs/2510.19851 #cs.CR #cs.AI

LLM Bazaar: A Service Design for Supporting Collaborative Learning with an LLM-Powered Multi-Party Collaboration Infrastructure https://arxiv.org/abs/2510.18877 #cs.HC #cs.AI

CityAQVis: Integrated ML-Visualization Sandbox Tool for Pollutant Estimation in Urban Regions Using Multi-Source Data (Software Article) https://arxiv.org/abs/2510.18878 #cs.HC #cs.LG

FIRETWIN: Digital Twin Advancing Multi-Modal Sensing, Interactive Analytics for Wildfire Response https://arxiv.org/abs/2510.18879 #cs.HC

Towards Better Health Conversations: The Benefits of Context-seeking https://arxiv.org/abs/2510.18880 #cs.HC #cs.CL #cs.CY

Detecting AI-Assisted Cheating in Online Exams through Behavior Analytics https://arxiv.org/abs/2510.18881 #cs.HC #cs.CY

Contextual Augmentation for Entity Linking using Large Language Models https://arxiv.org/abs/2510.18888 #cs.CL #cs.AI

Small Language Models Offer Significant Potential for Science Community https://arxiv.org/abs/2510.18890 #cs.CL #cs.AI

When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs https://arxiv.org/abs/2510.18892 #cs.CL #cs.LG

CodeCRDT: Observation-Driven Coordination for Multi-Agent LLM Code Generation https://arxiv.org/abs/2510.18893 #cs.DC #cs.AI #cs.SE