Published multiple papers including 'The BrowserGym Ecosystem for Web Agent Research', 'From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty', 'AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?', and more.
Research Experience
Currently interning at Meta FAIR (CodeGen); founding team member and research lead at Ask-AI, developing a generative AI sidekick that reasons over enterprise data; fortunate to have interned at Microsoft and AI2 during studies.
Education
PhD candidate in Computer Science (3rd year) at Tel Aviv University, advised by Prof. Jonathan Berant (2024 Google PhD Fellow)
Background
Research interests include Natural Language Processing, particularly in building and understanding systems that reason to perform complex tasks such as multi-hop question answering and multi-modal reasoning. Recent works focus on improving the performance, efficiency, and robustness of LLMs when augmented with external tools like search engines, code interpreters, and the entire web.