Ehsan Kamalloo

prof_pic.jpg

My name is Ehsan (pronounced /eh☀️/ or /ih☀️/, or even /e☀️/). I am a Senior Research Scientist in the Frontier AI Research team at ServiceNow AI Research.

I am broadly interested in building intelligent autonomous systems that are capable of complex reasoning (PipelineRL and TapeAgents). In particular, my work explores how learning and interaction can enable LLM agents to plan over long horizons, adapt to feedback, and operate effectively in multi-agent environments. Previously, my research focused on reliable evaluation (e.g. “LLM-as-a-judge for QA” at ACL’23 and SIGIR’24, and “MIRACL” at TACL’23).

Prior to ServiceNow, I was a Post-doctoral Fellow at the David R. Cheriton School of Computer Science, University of Waterloo, hosted by Jimmy Lin. I completed my PhD at the University of Alberta, advised by Davood Rafiei. I was also fortunate enough to collaborate with Charles Clarke and Siva Reddy. I also interned as a researcher at Huawei Noah’s Ark Lab in Montreal and worked with Mehdi Rezagholizadeh. Before PhD, I was working as a software engineer.

Interns

news

Feb 2026 :tada: REALM, workshop on LLM agents :robot:, returns for its 2nd edition at EMNLP 2026 in Budapest, Hungary.
Jan 2026 :tada: PipelineRL got accepted at TMLR.
Sep 2025 :mega: PipelineRL paper is out.
Jul 2025 REALM workshop on LLM agents, held at ACL 2025, Vienna :austria:: Accepted PapersRecordingsProceedings
May 2025 :mega: “Self-Evolving Curriculum” paper is out.
Apr 2025 :mega: PipelineRL, async RL training library with in-flight weight updates, is out: Blog
Jan 2025 REALM’s Call for Paper is out. Submissions are due March 31, 2025 April 02, 2025.
Nov 2024 Organizing REALM: First Workshop for Research on Agent Language Models at ACL 2025 in Vienna :violin:.