arXiv:2106.06060v4 Announce Type: replace-cross Abstract: Traditional competitive markets do not account for negative externalities; indirect costs that…
Category: AI
Can We Trust AI Agents? A Case Study of an LLM-Based Multi-Agent System for Ethical AI
arXiv:2411.08881v3 Announce Type: replace-cross Abstract: AI-based systems, including Large Language Models (LLMs), impact millions by supporting diverse…
KernelArc: A Multi-Agent Framework for GPU Kernel Optimization
arXiv:2608.17071v2 Announce Type: replace Abstract: We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across…
DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation
arXiv:2608.20114v2 Announce Type: replace Abstract: Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future…
FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents
arXiv:2608.18423v2 Announce Type: replace Abstract: Language model agents now execute bounded tasks reliably. Whether they can sustain effective…
The Lifecycle of LLM-as-a-Judge for Large-Scale Recommendation Explanations
arXiv:2608.18300v2 Announce Type: replace Abstract: LLM-as-a-Judge, which leverages a large language model to evaluate natural language generated by…
Attributing Preprocessing Invariance in Spectral Foundation Models
arXiv:2608.14227v2 Announce Type: replace Abstract: Preprocessing invariance is an appealing goal for spectral foundation models: a frozen model should…
Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces
arXiv:2608.11354v2 Announce Type: replace Abstract: Modern recommender systems treat observed actions as reliable proxies for user preferences, yet…
TRACE-Memory: Public-Conditioned Retrieval and Utility-Aware Evidence Admission for Personalized Generation
arXiv:2608.08446v2 Announce Type: replace Abstract: Personalized generation systems retrieve user history by request–memory relevance and inject it into…
MemWM: Memory-Augmented Text-Based World Model
arXiv:2608.07107v2 Announce Type: replace Abstract: World models are increasingly used to support planning in agents by predicting how environment states…