ServiceNow / AgentLab
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
β275Updated this week
Alternatives and similar repositories for AgentLab:
Users that are interested in AgentLab are comparing it to the libraries listed below
- WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?β168Updated last month
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycleβ237Updated this week
- ππͺ BrowserGym, a Gym environment for web task automationβ639Updated this week
- Code for the paper π³ Tree Search for Language Model Agentsβ185Updated 7 months ago
- AWM: Agent Workflow Memoryβ252Updated last month
- An agent benchmark with tasks in a simulated software company.β268Updated this week
- VisualWebArena is a benchmark for multimodal agents.β318Updated 4 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gymβ402Updated last week
- π Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Papβ¦β162Updated 3 months ago
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agentsβ189Updated this week
- β374Updated 2 months ago
- Building a comprehensive and handy list of papers for GUI agentsβ252Updated last week
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RLβ330Updated last month
- β184Updated 3 weeks ago
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agentsβ305Updated last month
- This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.β289Updated last week
- Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"β921Updated last month
- Code and Data for Tau-Benchβ346Updated 2 months ago
- Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactionβ265Updated 2 weeks ago
- β160Updated 7 months ago
- π€ Agent-as-a-Judge and DevAI datasetβ375Updated 2 months ago
- AndroidWorld is an environment and benchmark for autonomous agentsβ248Updated this week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"β300Updated 4 months ago
- Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"β463Updated last year
- [NeurIPS 2022] πWebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentsβ313Updated 6 months ago
- An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]β291Updated 10 months ago
- A curated collection of LLM reasoning and planning resources, including key papers, limitations, benchmarks, and additional learning mateβ¦β249Updated 3 weeks ago
- WebLINX is a benchmark for building web navigation agents with conversational capabilitiesβ144Updated last month