Grounding Open-Domain Instructions to Automate Web Support Tasks
Nancy Xu, Sam Masling, Michael Du, Giovanni Campagna, Larry Heck, James Landay, Monica Lam
- 🏛 Institutions
- Stanford, Viv Labs, Samsung Research
- 📅 Date
- March 30, 2021
- 📑 Publisher
- NAACL 2021
- 💻 Env
- Web
- 🔑 Keywords
TLDR
This paper introduces RUSS, a system for executing open-domain customer-support instructions on websites by parsing them into a ThingTalk representation and grounding webpage elements. It also contributes a dataset of 80 support problems with 741 step-by-step instructions and their corresponding actions.
Related papers
- LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration BenchmarkApril 18, 2025 · arXiv
- SheetCopilot: Bringing Software Productivity to the Next Level through Large Language ModelsMay 30, 2023 · NeurIPS 2023
- WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent BenchmarkApril 13, 2026 · arXiv
- WebArena-Infinity: Generating Browser Environments with Verifiable Tasks at ScaleMarch 2026 · Blog Post
- WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction TracesMarch 5, 2026 · arXiv
- Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web AgentsAugust 3, 2025 · ICLR 2026 (Poster)