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

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

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

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

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

Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups

This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.

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

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

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

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

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

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

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

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

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

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

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

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

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

Author implementation of the paper "Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing"

Repository for "Generating Sentences by Editing Prototypes"

The fastai deep learning library

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Simple examples to introduce PyTorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".