🤖 AI 前沿资讯

HuggingFace

FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills

Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures di...

AI 聚合

2026-08-22

arXiv

Prompt-Conditioned Channel Attention for Hierarchical Feature Modulation toward Anatomy-Agnostic Segmentation

Anatomically plausible segmentation remains challenging because of low contrast, ambiguous boundaries, and modality-s...

AI 聚合

2026-08-21

arXiv

Growth Without Us: Machine Consumers, Corporate Circularity, and the Decoupling of GDP from Humanity after AGI

The standard objection to full automation is demand-side: if humans earn nothing, who buys the output? This confuses ...

AI 聚合

2026-08-21

arXiv

Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models

Multimodal large language models (MLLMs) combine linguistic reasoning with visual perception, yet their ability to pe...

AI 聚合

2026-08-21

arXiv

QUASAR: A Quantum-Classical Neural Network for SAR Satellite Physical-Layer Authentication

X-band SAR satellites (8-12 GHz) play a critical role in disaster response, environmental monitoring, and military in...

AI 聚合

2026-08-21

arXiv

Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation

Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather tha...

AI 聚合

2026-08-21

arXiv

Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning

The rapid proliferation of memecoins on blockchain platforms has increased the risk of fraudulent activities, particu...

AI 聚合

2026-08-21

arXiv

Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents

Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable wi...

AI 聚合

2026-08-21

arXiv

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

Large language models often fail to answer questions about a bounded document collection when the source documents ar...

AI 聚合

2026-08-21

arXiv

Phantom Gains: Auditing Self-Improvement Against a Measured Null

Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual prob...

AI 聚合

2026-08-21

arXiv

MidTool: Mid-training Data Synthesis for Agentic Tool Use

Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Re...

AI 聚合

2026-08-21

arXiv

Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation

Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improv...

AI 聚合

2026-08-21