THUDM / WebRL
Building Open LLM Web Agents with Self-Evolving Online Curriculum RL
☆166Updated this week
Related projects ⓘ
Alternatives and complementary repositories for WebRL
- AWM: Agent Workflow Memory☆203Updated last month
- ☆116Updated 5 months ago
- Code for the paper 🌳 Tree Search for Language Model Agents☆138Updated 3 months ago
- Official Repo for UGround☆93Updated this week
- ☆283Updated last month
- An Analytical Evaluation Board of Multi-turn LLM Agents☆245Updated 5 months ago
- Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.☆254Updated last month
- 🤠 Agent-as-a-Judge and DevAI dataset☆184Updated last week
- [ACL 2024] AUTOACT: Automatic Agent Learning from Scratch for QA via Self-Planning☆177Updated last month
- Environments, tools, and benchmarks for general computer agents☆172Updated 2 weeks ago
- Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi e…☆346Updated 2 months ago
- ☆128Updated last week
- An implemtation of Everyting of Thoughts (XoT).☆129Updated 8 months ago
- FireAct: Toward Language Agent Fine-tuning☆254Updated last year
- ☆102Updated 2 months ago
- Offical Repo for "Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale"☆190Updated 3 weeks ago
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agents☆133Updated this week
- CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/☆187Updated this week
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆75Updated 3 weeks ago
- LongEmbed: Extending Embedding Models for Long Context Retrieval (EMNLP 2024)☆114Updated this week
- AndroidWorld is an environment and benchmark for autonomous agents☆125Updated this week
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆277Updated 3 weeks ago
- ☆135Updated 6 months ago
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆328Updated 4 months ago
- ☆493Updated 3 weeks ago
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆106Updated 2 weeks ago
- VisualWebArena is a benchmark for multimodal agents.☆236Updated this week
- This is the official repo for "PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization". PromptAgen…☆199Updated 3 months ago
- Self-playing Adversarial Language Game Enhances LLM Reasoning, NeurIPS 2024☆95Updated this week
- This is a collection of resources for computer-use agents, including videos, blogs, papers, and projects.☆85Updated this week