Jonathan Berant · page 2
Papers
- AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks? (2024 · 46 citations)
The paper asks whether LM-based web agents can handle realistic, multi-step information-seeking tasks on the open web, such as tracking housing prices or finding a nearby gym with a suitable class schedule. - Dolomites: Domain-Specific Long-Form Methodical Tasks (2025 · 12 citations)
Professionals such as clinicians, lawyers and teachers often produce structured documents (care plans, petitions, lesson plans) by following a fairly fixed routine. - A Simple Global Neural Discourse Parser (2020)
The paper addresses document-level discourse parsing in the RST framework. Most existing parsers are greedy and depend on hand-built features or extra resources, because exact global search is expensive: a node's relation and nuclearity labels depend on where its children are split. The authors build a CKY-style…
This page in Markdown → https://md.research.elamur.ai/free/en/authors/jonathan-berant/page/2/