arXiv:2509.04827v2 Announce Type: replace-cross Abstract: Modern Large Language Model (LLM) serving systems increasingly support interactive applications, like real-time chat assistants, code generation tools, and agentic workflows. However, the soaring energy cost of LLM inference presents a growing challenge for sustainable…
arXiv:2509.11067v1 Announce Type: new Abstract: Autonomous agents for desktop automation struggle with complex multi-step tasks due to poor coordination and inadequate quality control. We introduce textsc{Agentic Lybic}, a novel multi-agent system where the entire architecture operates as a finite-state machine…
arXiv:2509.11661v1 Announce Type: cross Abstract: Intelligent tableware cleaning is a critical application in food safety and smart homes, but existing methods are limited by coarse-grained classification and scarcity of few-shot data, making it difficult to meet industrialization requirements. We propose…
arXiv:2509.11068v1 Announce Type: new Abstract: The landscape of Large Language Models (LLMs) shifts rapidly towards dynamic, multi-agent systems. This introduces a fundamental challenge in establishing computational trust, specifically how one agent can verify that another’s output was genuinely produced by…
arXiv:2509.11942v1 Announce Type: cross Abstract: Visual documentation is an effective tool for reducing the cognitive barrier developers face when understanding unfamiliar code, enabling more intuitive comprehension. Compared to textual documentation, it provides a higher-level understanding of the system structure and…
arXiv:2509.11078v1 Announce Type: new Abstract: Synthetic data generation using large language models (LLMs) has emerged as a promising solution across various domains, particularly in medical field, to mitigate data collection challenges. However, existing studies mainly utilize LLMs to rewrite and…
arXiv:2509.12081v1 Announce Type: cross Abstract: This paper proposes deception as a mechanism for out-of-distribution (OOD) generalization: by learning data representations that make training data appear independent and identically distributed (iid) to an observer, we can identify stable features that eliminate…
arXiv:2509.11079v1 Announce Type: new Abstract: Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent frameworks often rely on static or task-level workflows, which either over-process simple queries or underperform on complex ones, while…
arXiv:2509.12190v1 Announce Type: cross Abstract: When survival instincts conflict with human welfare, how do Large Language Models (LLMs) make ethical choices? This fundamental tension becomes critical as LLMs integrate into autonomous systems with real-world consequences. We introduce DECIDE-SIM, a novel…
arXiv:2509.11131v1 Announce Type: new Abstract: Neural Cellular Automata (NCA) represent a powerful framework for modeling biological self-organization, extending classical rule-based systems with trainable, differentiable (or evolvable) update rules that capture the adaptive self-regulatory dynamics of living matter. By embedding Artificial…
