Archives AI News

Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN

arXiv:2412.17629v4 Announce Type: replace-cross Abstract: Evolutionary algorithms (EAs) simulate natural selection but have two main limitations: (1) they rarely update individuals based on global correlations, limiting comprehensive learning; (2) they struggle with balancing exploration and exploitation, where excessive exploitation causes…

H$^2$R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents

arXiv:2509.12810v1 Announce Type: new Abstract: Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as monolithic units, leading…

Zero-shot Graph Reasoning via Retrieval Augmented Framework with LLMs

arXiv:2509.12743v1 Announce Type: new Abstract: We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a wide range of graph reasoning…

Large Language Models Imitate Logical Reasoning, but at what Cost?

arXiv:2509.12645v1 Announce Type: new Abstract: We present a longitudinal study which evaluates the reasoning capability of frontier Large Language Models over an eighteen month period. We measured the accuracy of three leading models from December 2023, September 2024 and June…

ECG-aBcDe: Overcoming Model Dependence, Encoding ECG into a Universal Language for Any LLM

arXiv:2509.12625v1 Announce Type: new Abstract: Large Language Models (LLMs) hold significant promise for electrocardiogram (ECG) analysis, yet challenges remain regarding transferability, time-scale information learning, and interpretability. Current methods suffer from model-specific ECG encoders, hindering transfer across LLMs. Furthermore, LLMs struggle…

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors

arXiv:2509.13237v1 Announce Type: cross Abstract: Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought. During the process, they often re-derive the same intermediate steps across problems, inflating token usage and latency. This saturation of the…

Mob-based cattle weight gain forecasting using ML models

arXiv:2509.12615v1 Announce Type: new Abstract: Forecasting mob based cattle weight gain (MB CWG) may benefit large livestock farms, allowing farmers to refine their feeding strategies, make educated breeding choices, and reduce risks linked to climate variability and market fluctuations. In…