First Workshop for Research on Agent Language Models (REALM) at ACL 2025

Large language models (LLMs) have become a workhorse to drive intelligent agents to a higher level of agency, autonomy, and self-direction. As a result, we have witnessed a surge in LLM agents across many diverse environments including web navigation (WebArena and WorkArena), mobile applications (Mobile-Agent), protein discovery (ProtoAgent), cybersecurity (Cybench) and even scientific research (MLAgentBench). In addition, integrating various services and more advanced architecture including external tools (e.g. function calling, APIs), memory (e.g. MemGPT), external or private knowledge integration (RAG, and RETRO), advanced planning (Chain-of-Thought, ReAct, Reflection, self-critic, etc.) and multi-agent collaboration into agents has enabled them to accomplish even more complex goals. Despite these advancements, introducing this level of autonomy and complexity at large scale or in production, brings unprecedented challenges to build, configure, deploy, evaluate, collaborate and improve LLM agents safely and responsibly.

Our workshop aims to bring together researchers, practitioners, and thought leaders in the ACL community to discuss and align on the current landscape, key challenges, and future directions of LLM agents.

Venue

The REALM workshop will take place at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), in Vienna, Austria. The conference will take place from July 27th to August 1st, 2025. Workshops will be held July 31st and August 1st. For more details about ACL 2025, check their website.

The REALM Workshop will be on July 31st at the Austria Center in Vienna in room 1.61-62. Please see the full schedule for all details.

Important Dates

  • Submission Deadline: Monday March 31st, 2025 Wednesday April 2nd, 2025
  • Notification of Acceptance: Wednesday May 14th, 2025
  • Camera Ready Deadline: Monday June 2nd, 2025
  • Workshop Date: July 31, 2025

All deadlines are calculated at 11:59pm Anywhere on Earth (UTC-12).

Invited Speakers and Panelists

We have an exciting lineup of speakers and panelists.

Image
Nicolas Chapados
ServiceNow Research
Image
Daniel Fried
Carnegie Mellon University
Image
Chris Manning
Stanford University
Image
Roberta Raileanu
Google DeepMind
Image
Siva Reddy
McGill University / Mila
Image
Yu Su
Ohio State University
Image
Diyi Yang
Stanford University
Image
Tao Yu
University of Hong Kong

Questions

If you have any questions, please do not hesitate to contact us at [email protected].

Organizers

Image
Ehsan Kamalloo
ServiceNow Research
Image
Nicolas Gontier
ServiceNow Research
Image
Xing Han Lu
McGill University / Mila
Image
Shikhar Murty
Stanford University
Image
Alexandre Lacoste
ServiceNow Research
Image
Nouha Dziri
Ai2

Advisory Board

Image

Hannaneh Hajishirzi

University of Washington / Ai2
Image

Graham Neubig

Carnegie Mellon University / All Hands AI