Quality follows upgrading
Category
arXiv:2603.11245v1 Announce Type: new Abstract: As NLP evaluation shifts from static benchmarks to multi-turn interactive settings, LLM-based simulators have become widely used as user proxies, …
arXiv:2603.11239v1 Announce Type: new Abstract: The dynamic evolution of real-world necessitates model editing within Large Language Models. While existing methods explore modular isolation or parameter-efficient …
arXiv:2603.11214v1 Announce Type: new Abstract: We evaluate the autonomous cyber-attack capabilities of frontier AI models on two purpose-built cyber ranges-a 32-step corporate network attack and …
arXiv:2603.11178v1 Announce Type: new Abstract: Standard LLM distillation wastes compute on two fronts: problems the student has already mastered (near-zero gradients) and problems far beyond …
arXiv:2603.11093v1 Announce Type: new Abstract: The development of high-level autonomous driving (AD) is shifting from perception-centric limitations to a more fundamental bottleneck, namely, a deficit …
arXiv:2603.11076v1 Announce Type: new Abstract: Recent work synthesizes agentic tasks for post-training tool-using LLMs, yet robust generalization under shifts in tasks and toolsets remains an …
arXiv:2603.11495v1 Announce Type: new Abstract: Tool-calling empowers Large Language Models (LLMs) to interact with external environments. However, current methods often struggle to handle massive and …
arXiv:2603.11513v1 Announce Type: new Abstract: Retrieval augmented generation RAG is widely deployed to improve factual accuracy in language models yet it remains unclear whether smaller …
arXiv:2603.11545v1 Announce Type: new Abstract: We present an agentic AI framework for autonomous multimodal query processing that coordinates specialized tools across text, image, audio, video, …
arXiv:2603.11564v1 Announce Type: new Abstract: The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV …
arXiv:2603.11578v1 Announce Type: new Abstract: Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We …
arXiv:2603.11583v1 Announce Type: new Abstract: The success of a Large Language Model (LLM) task depends heavily on its prompt. Most use-cases specify prompts using natural …