arXiv Computer Science @arxiv_cs@qoto.org

Sum of rank ratios: an alternative to percentiles for research assessment, from groundbreaking to mainstream research https://arxiv.org/abs/2605.17023 #cs.DL #cs.SI

Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road https://arxiv.org/abs/2605.17026 #cs.LG

PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts https://arxiv.org/abs/2605.17028 #cs.CL #cs.AI

Task Abstention for Large Language Models in Code Generation https://arxiv.org/abs/2605.17029 #cs.SE #cs.AI

A Joint Synthetic Housing-Household Inventory https://arxiv.org/abs/2605.17031 #cs.CY

Generalizable and Actionable Parts Pose Estimation with Symmetry Annotation-Free Learning Strategy https://arxiv.org/abs/2605.17033 #cs.RO

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation https://arxiv.org/abs/2605.17034 #cs.LG #cs.AI #cs.CR

Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management https://arxiv.org/abs/2605.17036 #eess.SY #cs.AI #cs.LG #cs.MA #cs.SY

D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning https://arxiv.org/abs/2605.17037 #cs.LG #cs.AI #cs.CL

DeepSlide: From Artifacts to Presentation Delivery https://arxiv.org/abs/2605.15202 #cs.AI #cs.CL #cs.IR

Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation https://arxiv.org/abs/2605.15203 #cs.IR #cs.AI #cs.MA

SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch https://arxiv.org/abs/2605.15204 #cs.AI

Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations https://arxiv.org/abs/2605.15205 #cs.AI

AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices https://arxiv.org/abs/2605.15206 #cs.LG #cs.AI #cs.DC

TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination https://arxiv.org/abs/2605.15207 #cs.LG #cs.MA

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels https://arxiv.org/abs/2605.15208 #cs.LG #cs.AI

Fault tolerance estimation in digital circuits with visualised generative networks https://arxiv.org/abs/2605.15212 #cs.AR #cs.AI #cs.CE

An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendations https://arxiv.org/abs/2605.15213 #cs.IR #cs.AI

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces https://arxiv.org/abs/2605.15215 #cs.AI #cs.SE

GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration https://arxiv.org/abs/2605.13848 #cs.AI #cs.CL #cs.DC