PathOnAI.org

Excited to introduce LiteWebAgent, an open-source suite for VLM-based web agents showcased at NAACL 2025 this week! This project offers a range of key features: - Extensible agent framework incorporating planning, memory & tree search capabilities - FastAPI integration enabling serverless deployment - Interactive UI featuring voice control & real-time visualization - Flexible deployment options including web app & Chrome extension LiteWebAgent serves as a bridge between research and practical application, equipping users with all the essentials for real-world web agent implementations. 📄 Paper: Read more about the project here: aclanthology.org/2025.naacl-dem… 🔗 Project: Explore LiteWebAgent on PathOnAI.org: pathonai.org/projects/litew… ⭐ GitHub: Access the project repository on GitHub: github.com/PathOnAI/LiteW… Additionally, we have recently wrapped up VisualTreeSearch, our subsequent endeavor focusing on interpretable tree search within web agents. Learn more about this follow-up project here: lnkd.in/gbWDdJed #WebAgents #NAACL2025 #PathOnAI

We have added the general application on our website @PathOnAI : pathonai.org/opportunities. If you are interested in the research opportunity, please check pathonai.org/opportunities/…. If you are generally interested in PathOnAI.org, please check pathonai.org/opportunities/…. We would appreciate if you take some time to fill in the forms even if you have talked with me or other team members, as we've built a system to track applications and will update on a rolling basis. Thank you!

TL;DR: we are excited to release a powerful new open-weight language model with reasoning in the coming months, and we want to talk to devs about how to make it maximally useful: openai.com/open-model-fee… we are excited to make this a very, very good model! __ we are planning to release our first open-weigh language model since GPT-2. we’ve been thinking about this for a long time but other priorities took precedence. now it feels important to do. before release, we will evaluate this model according out our preparedness framework, like we would for any other model. and we will do extra work given that we know this model will be modified post-release. we still have some decisions to make, so we are hosting developer events to gather feedback and later play with early prototypes. we’ll start in SF in a couple of weeks followed by sessions in europe and APAC. if you are interested in joining, please sign up at the link above. we’re excited to see what developers build and how large companies and governments use it where they prefer to run a model themselves.

写了一篇中文博客: 从零开始运营一个开源AGI科研社区：PathOnAI.org的实践与思考danqingz.github.io/blog/2025/03/2…