[ACL 2026 Main] Official repository for paper: OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents
☆48Apr 7, 2026Updated 5 months ago
Alternatives and similar repositories for OS-Symphony
Users that are interested in OS-Symphony are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ACL 2026] Code, benchmark and environment for "OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic…☆49Jul 5, 2026Updated 2 months ago
- ☆24Jun 13, 2023Updated 3 years ago
- Extremely Long-Horizon Agentic Tasks Requiring Active Acting and Inductive Reasoning☆34Feb 9, 2026Updated 7 months ago
- Open-source framework for computer use agents: VeriGen verifiable task synthesis, online RL training (AgentRL), and OSWorld/ScienceBoard …☆58Aug 3, 2026Updated last month
- ☆18Jul 31, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for "From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios"☆27Jun 7, 2026Updated 3 months ago
- [ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis☆190Oct 8, 2025Updated 11 months ago
- ☆33Oct 18, 2024Updated last year
- [NeurIPS 2024 poster] Cross-model Control: Improving Multiple Large Language Models in One-time Training☆15Oct 25, 2024Updated last year
- The model, data and code for OpenMobile☆50Jul 9, 2026Updated 2 months ago
- Official repo of "MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents". It can be used to evaluate a GUI agent w…☆115Sep 8, 2025Updated last year
- ☆36Jan 28, 2026Updated 7 months ago
- MacAgentBench: Benchmark agents where they actually work — on macOS.☆50Jun 21, 2026Updated 2 months ago
- Advancing Block Diffusion Language Models for Test-Time Scaling☆16Feb 14, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR'2026] R-HORIZON: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?☆18Oct 21, 2025Updated 10 months ago
- OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks☆317Updated this week
- DART-GUI: Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation☆97Feb 26, 2026Updated 6 months ago
- EvoCUA: Evolving Computer Use Agent☆347Mar 31, 2026Updated 5 months ago
- A Self-Training Framework for Vision-Language Reasoning☆90Jan 23, 2025Updated last year
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆72Jun 1, 2025Updated last year
- An Arena-style Automated Evaluation Benchmark for Detailed Captioning☆58Jun 1, 2025Updated last year
- [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆178Jun 18, 2026Updated 3 months ago
- CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents☆74Sep 3, 2026Updated 2 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official Implementation for *PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling*☆43Dec 13, 2025Updated 9 months ago
- ☆18Mar 26, 2026Updated 5 months ago
- OpenMMLab Detection Toolbox and Benchmark for V3Det☆15Apr 3, 2024Updated 2 years ago
- Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents☆200Aug 13, 2026Updated last month
- CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning☆37Aug 28, 2025Updated last year
- [ICLR 2026] Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"☆137Feb 2, 2026Updated 7 months ago
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories☆49Aug 16, 2026Updated last month
- [ACL 2025] A Neural-Symbolic Self-Training Framework☆117Jun 1, 2025Updated last year
- Code for paper OpenWebRL: Online Multi-Turn Reinforcement Learning for Visual Web Agents☆51Aug 17, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆66Sep 6, 2025Updated last year
- Sparse Multilabel Categorical Crossentropy☆11Sep 10, 2023Updated 3 years ago
- An Autonomous Curriculum Reinforcement Learning framework that steers agents to continually learn in specific environments with zero huma…☆44Jun 7, 2026Updated 3 months ago
- ☆10Mar 11, 2024Updated 2 years ago
- ☆10Mar 22, 2024Updated 2 years ago
- MiroEval: A benchmark and evaluation framework for deep research agents — 100 tasks (70 text, 30 multimodal) assessed across synthesis qu…☆50Jul 6, 2026Updated 2 months ago
- ☆12Aug 8, 2024Updated 2 years ago