Rob Tang
@XiangruTang
Final-year CS PhD student @Yale. Research intern @google. This account is for academic purposes.
🔥Excited to share our latest work: Agent KB It achieves new open-source SOTA on the GAIA benchmark! We enable agents to learn from each other's experiences across tasks through hierarchical experience sharing. Paper📜: huggingface.co/papers/2507.06… Code🧑💻: github.com/OPPO-PersonalA…
ACL 2025 poster “LocAgent: Agentic Code Localization with Graph-Based Indexing”! 📍 Hall 4/5 – Session 2: IP-Posters 🗓️ Monday, July 28 | 11:00–12:30 👋 Come chat with us in person—we’d love to connect! #ACL2025
I'm excited to share insights from our new work: LocAgent! We've developed a graph-guided agentic framework that significantly advances code localization capabilities. 🔍 The Problem Code localization (finding exactly where changes need to be made) is a fundamental challenge for…
We explore how LLM agents can support medical decisions and automate scientist’s workflows. ｛Medagents+BioCoder+MedAgents｝ looking forward to more!
Posting my talk on Mon. on Cancer Genomics at the Institut Curie lectures.gersteinlab.org/summary/Char-P… Lots of new slides (by @XiangruTang) on using LLMs for "tumor boards" & for generating genomics workflows
volunteer at Google booth #ICML25 as a research intern and then grab a drink!
🚀 Just discovered an amazing app for vibe coding! @_akhaliq ✨ Describe your app in plain English → Get complete HTML/CSS/JS code 🖼️ Upload UI designs → Auto-generate code 🌐 One-click deploy and Free to use with multiple LLMs! 👉 huggingface.co/spaces/akhaliq…
those improvements are nothing to scoff at. really impressive "Claude-3.7 with Agent KB increased performance from 38.46% to 57.69%, while GPT-4.1 showed similar improvements on intermediate tasks (53.49% to 73.26%). For SWE-bench code repair tasks, our system significantly…