1

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

Qwen2.5-VL Technical Report

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

OpenAgents: An Open Platform for Language Agents in the Wild

Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning

Binding Language Models in Symbolic Languages

In-Context Learning for Few-Shot Dialogue State Tracking

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models