Natural Language Processing
xlang-ai/OSWorld🔥 active
▲ +5 ★ this week
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
🤖 Language Models
PythonApache-2.0updated Nov 12, 2026
[NeurIPS 2024] Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
$ git clone https://github.com/xlang-ai/Spider2-V.git▲ +5 ★ this week
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
▲ +9 ★ this week
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
[NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis
[ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
DialOp: Decision-oriented dialogue environments for collaborative language agents
Data from GitHub · snapshot Nov 13, 2026