xlang-ai

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

[ICLR 2025 Oral] Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents

[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

[ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Paper collection on building and evaluating language model agents via executable language grounding

[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"

[ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".

Qwen-CUA: Native Computer Use for (Almost) Everything — a screenshot-driven agent that operates computers with keyboard and mouse, jointly developed by the Qwen Team and XLang Lab.

Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents

[ICLR 2025] BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

[ICLR 2024 Spotlight] Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

[NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis

[NeurIPS 2024] Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"

NeurIPS2026 , Scalable annotation pipeline for action-aglined fine-grained instruciton for Visual-language-Action model

CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents

[EMNLP 2023 Industry Track] A simple prompting approach that enables the LLMs to run inference in batches.

[ICLR 2026] Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use Agents

[ICLR2025 Spotlight] Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

This is the official code base of AgentNetTool in OpenCUA. Website: https://opencua.xlang.ai/

The official repo of VideoAgentTrek