XLANG Lab

OpenAgents

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

OSWorld

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

instructor-embedding

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

Spider2

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

UnifiedSKG

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

OpenCUA

OpenCUA: Open Foundations for Computer-Use Agents

aguvis

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

xlang-paper-reading

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

Binder

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

DS-1000

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

text2reward

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

BRIGHT

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

Spider2-V

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

OSWorld-G

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

icl-selective-annotation

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

batch-prompting

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

EVOR

computer-agent-arena

Computer Agent Arena: Test & compare AI agents in real desktop apps & web environments. Code/data coming soon!

AgentTrek

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

VideoAgentTrek

The official repo of VideoAgentTrek

AgentNetTool

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

diagrams_toolkit

Source code for diagrams in the paper of NLPers from HKU.

xlang-ai.github.io

The official website of xlang.ai

.github

verl

veRL: Volcano Engine Reinforcement Learning for LLM

Pai-Megatron-Patch

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.