Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay
☆155May 29, 2025Updated 10 months ago
Alternatives and similar repositories for ARPO
Users that are interested in ARPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆13Nov 5, 2024Updated last year
- [EMNLP 2025] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning☆79Nov 4, 2025Updated 5 months ago
- ZeroGUI: Automating Online GUI Learning at Zero Human Cost☆117Jul 17, 2025Updated 8 months ago
- [NeurIPS 2025] A multimodal agent that can interact with its own PC in a multimodal manner.☆36Feb 25, 2026Updated last month
- [ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents☆27Feb 17, 2026Updated last month
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆32Jul 3, 2025Updated 9 months ago
- R1-like Computer-use Agent☆89Mar 21, 2025Updated last year
- Repository of GUI Action Narrator☆13Apr 8, 2025Updated last year
- [ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)☆934Jan 28, 2026Updated 2 months ago
- ☆129Oct 3, 2025Updated 6 months ago
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆306Mar 11, 2026Updated last month
- ☆22May 3, 2025Updated 11 months ago
- An Autonomous Curriculum Reinforcement Learning framework that steers agents to continually learn in specific environments with zero huma…☆26Feb 25, 2026Updated last month
- OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents☆24Jan 6, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments☆2,757Apr 2, 2026Updated last week
- ☆14Mar 5, 2024Updated 2 years ago
- Multimodal computer agent data collection program☆167Dec 5, 2025Updated 4 months ago
- SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward☆93Aug 8, 2025Updated 8 months ago
- ☆73Jun 10, 2025Updated 10 months ago
- ☆34Aug 17, 2025Updated 7 months ago
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆1,780Feb 27, 2026Updated last month
- ☆41Jul 21, 2024Updated last year
- [NeurIPS 2024] Data exporter for SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset☆16Nov 8, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing☆10Jun 1, 2022Updated 3 years ago
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories☆42Aug 7, 2025Updated 8 months ago
- [AAAI 2026] Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks☆43Nov 24, 2025Updated 4 months ago
- MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning☆772Sep 7, 2025Updated 7 months ago
- [ICLR 2026] "VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?", Yuanxin Liu, Kun Ouyang, Haoning Wu, Yi Liu, L…☆37Jan 30, 2026Updated 2 months ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆515Jun 6, 2025Updated 10 months ago
- Code for CVPR22 paper One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones☆13Jul 27, 2022Updated 3 years ago
- ☆119Apr 8, 2025Updated last year
- A deep research framework☆26Feb 3, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆102May 20, 2025Updated 10 months ago
- Website for HKU NLP group (under construction)☆14Mar 20, 2026Updated 3 weeks ago
- [AAAI 2026]Release of code, datasets and model for our work TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for General…☆88Dec 1, 2025Updated 4 months ago
- Setup scripts for the WebArena benchmark☆20Jun 19, 2025Updated 9 months ago
- [ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control☆68Jan 7, 2026Updated 3 months ago
- Code for paper Empowering Large Language Model Agents through Action Learning☆33Aug 8, 2024Updated last year
- ☆528Feb 4, 2026Updated 2 months ago