McGill-NLP / weblinxLinks
WebLINX is a benchmark for building web navigation agents with conversational capabilities
☆157Updated 7 months ago
Alternatives and similar repositories for weblinx
Users that are interested in weblinx are comparing it to the libraries listed below
Sorting:
- Code for the paper 🌳 Tree Search for Language Model Agents☆217Updated last year
- ☆41Updated last year
- AWM: Agent Workflow Memory☆326Updated 8 months ago
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆144Updated 10 months ago
- [ICLR 2025] A trinity of environments, tools, and benchmarks for general virtual agents☆219Updated 3 months ago
- ☆81Updated 11 months ago
- ☆125Updated last year
- Multimodal computer agent data collection program☆149Updated last year
- ☆86Updated last year
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agents☆385Updated 5 months ago
- ☆122Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- Challenges for general-purpose web-browsing AI agents☆65Updated 4 months ago
- Official code for the paper "ADaPT: As-Needed Decomposition and Planning with Language Models"☆88Updated last year
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆278Updated 2 months ago
- [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆111Updated 3 months ago
- A codebase for "Language Models can Solve Computer Tasks"☆236Updated last year
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆64Updated 9 months ago
- Code for ScribeAgent paper☆61Updated 7 months ago
- ☆123Updated 7 months ago
- An implemtation of Everyting of Thoughts (XoT).☆150Updated last year
- 🔧 Compare how Agent systems perform on several benchmarks. 📊🚀☆102Updated 2 months ago
- Framework and toolkits for building and evaluating collaborative agents that can work together with humans.☆99Updated this week
- VisualWebArena is a benchmark for multimodal agents.☆386Updated 10 months ago
- Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)☆187Updated last month
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆128Updated last year
- Interaction-first method for generating demonstrations for web-agents on any website☆50Updated 5 months ago
- ☆56Updated 3 months ago
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆53Updated 9 months ago
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆250Updated last month