arXiv Computer Science @arxiv_cs@qoto.org

From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness https://arxiv.org/abs/2602.12285 #cs.CL #cs.AI

Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction https://arxiv.org/abs/2602.12287 #eess.AS #cs.CL #cs.AI

Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance https://arxiv.org/abs/2602.12288 #eess.SY #cs.AI #cs.RO #cs.SY

String-Level Ground Fault Localization for TN-Earthed Three-Phase Photovoltaic Systems https://arxiv.org/abs/2602.12289 #eess.SY #eess.SP #cs.LG #cs.SY

Design Environment of Quantization-Aware Edge AI Hardware for Few-Shot Learning https://arxiv.org/abs/2602.12295 #cs.AR

Adaptive traffic signal control optimization using a novel road partition and multi-channel state representation method https://arxiv.org/abs/2602.12296 #eess.SY #cs.AI #cs.SY

Fast and General Automatic Differentiation for Finite-State Methods https://arxiv.org/abs/2602.12300 #cs.FL

Beyond Musical Descriptors: Extracting Preference-Bearing Intent in Music Queries https://arxiv.org/abs/2602.12301 #eess.AS #cs.SD #cs.CL #cs.IR #cs.LG

Methodological Variation in Studying Staff and Student Perceptions of AI https://arxiv.org/abs/2602.11158 #cs.HC #cs.AI #cs.CY

Explaining AI Without Code: A User Study on Explainable AI https://arxiv.org/abs/2602.11159 #cs.AI #cs.HC #cs.LG

BIRD: A Museum Open Dataset Combining Behavior Patterns and Identity Types to Better Model Visitors' Experience https://arxiv.org/abs/2602.11160 #cs.HC #cs.AI #cs.IR

Althea: Human-AI Collaboration for Fact-Checking and Critical Reasoning https://arxiv.org/abs/2602.11161 #cs.HC #cs.CL

Retrieval Heads are Dynamic https://arxiv.org/abs/2602.11162 #cs.CL

Nested Named Entity Recognition in Plasma Physics Research Articles https://arxiv.org/abs/2602.11163 #cs.CL #cs.AI

Automated Optimization Modeling via a Localizable Error-Driven Perspective https://arxiv.org/abs/2602.11164 #cs.LG #cs.AI #cs.CL

Assessing LLM Reliability on Temporally Recent Open-Domain Questions https://arxiv.org/abs/2602.11165 #cs.CL #cs.AI

Reviewing the Reviewer: Elevating Peer Review Quality through LLM-Guided Feedback https://arxiv.org/abs/2602.10118 #cs.CL #cs.CY

Large Language Models Predict Functional Outcomes after Acute Ischemic Stroke https://arxiv.org/abs/2602.10119 #cs.LG #cs.AI #cs.CL #cs.CY

A Practical Guide to Agentic AI Transition in Organizations https://arxiv.org/abs/2602.10122 #cs.CY #cs.AI

How segmented is my network? https://arxiv.org/abs/2602.10125 #stat.AP #cs.SI #cs.NI