arXiv Computer Science @arxiv_cs@qoto.org

Conversational Agents for Building Energy Efficiency -- Advising Housing Cooperatives in Stockholm on Reducing Energy Consumption https://arxiv.org/abs/2511.08587 #cs.CY #cs.AI #cs.CL

Where did you get that? Towards Summarization Attribution for Analysts https://arxiv.org/abs/2511.08589 #cs.CL #cs.AI

GMTRouter: Personalized LLM Router over Multi-turn User Interactions https://arxiv.org/abs/2511.08590 #cs.CL #cs.LG

The Collective Turing Test: Large Language Models Can Generate Realistic Multi-User Discussions https://arxiv.org/abs/2511.08592 #cs.CL #cs.AI

Knowledge Graph Analysis of Legal Understanding and Violations in LLMs https://arxiv.org/abs/2511.08593 #cs.CL

Diverse Preference Learning for Capabilities and Alignment https://arxiv.org/abs/2511.08594 #cs.CL

Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning https://arxiv.org/abs/2511.08595 #cs.CL #cs.AI

What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge https://arxiv.org/abs/2511.08596 #cs.CL #cs.AI #cs.CY

Self-HarmLLM: Can Large Language Model Harm Itself? https://arxiv.org/abs/2511.08597 #cs.CL #cs.AI

OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking https://arxiv.org/abs/2511.08598 #cs.CL #cs.AI

Towards Affordable, Adaptive and Automatic GNN Training on CPU-GPU Heterogeneous Platforms https://arxiv.org/abs/2511.07421 #cs.DC

From Attention to Disaggregation: Tracing the Evolution of LLM Inference https://arxiv.org/abs/2511.07422 #cs.DC

Synera: Synergistic LLM Serving across Device and Cloud at Scale https://arxiv.org/abs/2511.07423 #cs.DC #cs.AI #cs.LG

Enhancing reliability in AI inference services: An empirical study on real production incidents https://arxiv.org/abs/2511.07424 #cs.DC #cs.CY

An Evaluation of LLMs Inference on Popular Single-board Computers https://arxiv.org/abs/2511.07425 #cs.DC #cs.AI

Network and Systems Performance Characterization of MCP-Enabled LLM Agents https://arxiv.org/abs/2511.07426 #cs.DC #cs.AI #cs.CL #cs.NI #cs.SE

DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones https://arxiv.org/abs/2511.07427 #cs.DC #cs.AI

Resource Allocation in Hybrid Radio-Optical IoT Networks using GNN with Multi-task Learning https://arxiv.org/abs/2511.07428 #cs.NI #cs.LG

Knowledge-Guided Textual Reasoning for Explainable Video Anomaly Detection via LLMs https://arxiv.org/abs/2511.07429 #cs.CV #cs.AI

Analysing Environmental Efficiency in AI for X-Ray Diagnosis https://arxiv.org/abs/2511.07436 #cs.AI