2 papers
cs.CV2026
GraphVerse: A Comprehensive Visual Graph Reasoning Benchmark for Multimodal Large Language Models
Yuanfu Sun, Yuanhang Ren, Kang Li +5
Recent Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse vision-language tasks, creating an urgent need for more challenging benchmarks. Yet…
cs.AI2026
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
Jiaxi Li, Ke Deng, Yun Wang +5
Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks. A growing line of work studies online skill learning, where agents c…