Archives AI News

What is the Visual Cognition Gap between Humans and Multimodal LLMs?

arXiv:2406.10424v2 Announce Type: replace-cross Abstract: Recently, Multimodal Large Language Models (MLLMs) and Vision Language Models (VLMs) have shown great promise in language-guided perceptual tasks such as recognition, segmentation, and object detection. However, their effectiveness in addressing visual cognition problems that…

ASP-FZN: A Translation-based Constraint Answer Set Solver

arXiv:2507.22774v3 Announce Type: replace Abstract: We present the solver asp-fzn for Constraint Answer Set Programming (CASP), which extends ASP with linear constraints. Our approach is based on translating CASP programs into the solver-independent FlatZinc language that supports several Constraint Programming…

Neural cellular automata: applications to biology and beyond classical AI

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…

Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm

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…

Difficulty-Aware Agent Orchestration in LLM-Powered Workflows

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…

Patient-Zero: A Unified Framework for Real-Record-Free Patient Agent Generation

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…

VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems

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…