Call For Papers

REALM’25 invites authors to submit 4-page or 8-page (short/long) papers about their work at the intersection of AI Agents and LLMs. Topics of interest include, but are not limited to:

  • Planning, Reasoning, and Decision-Making: Mechanisms and models that empower LLM agents to make plans, reason, backtrack, and take independent decisions in dynamic environments.
  • Agent Quality Evaluation: Methodologies to assess the agent performance and to guide their improvement.
  • Data and simulation environments: Data architectures, datasets and simulated environments for building LLM agents.
  • Agent-optimized LLMs: Training, fine-tuning and prompting of LLMs towards desired agentic behaviors.
  • Agent Architectures: Design and implementation of architectural frameworks that support agency in LLMs, enabling flexibility, scalability, and robustness in various tasks.
  • Human-Agent and Agent-Agent Interaction: Studies on how LLM agents interact with humans and other agents, including collaboration, feedback, learning, trust, and user experience. Multi-agent systems.
  • Safety and Robustness: Ensuring the reliability and safety of agentic LLM systems against adversarial scenarios and malicious use.
  • Ethics and Governance: Frameworks and guidelines for the ethical development, deployment, and oversight of agentic LLM systems.

Submission Guidelines

We invite the following types of submissions:

  • Long papers must be original unpublished work, with concrete evaluation and analysis. They can be up to 8 (eight) pages, plus unlimited pages of references and an appendix.
  • Short papers should be original unpublished work, including a small focused contribution, a negative result, an opinion piece, or an interesting application. They can be of up to 4 (four) pages of content with unlimited pages of references and appendix.

All submissions should be anonymous and must follow ACL formatting guidelines. The ACL 2025 templates must be used; these are provided in LaTeX and also Microsoft Word format.

Submissions will only be accepted in PDF format. The peer review will be double-blind. We consider both archival and non-archival submissions, however, note that only accepted archival papers will be included in the proceedings. The workshop accepts work that is under review or has already been published in or accepted for publication in any other peer-reviewed venue. These papers can be submitted to the workshop as non-archival submissions. Papers published on arXiv are also allowed to be submitted to the workshop (both as archival and non-archival).

All submissions have to be made through the following Openreview link.

Authors should be aware of OpenReview’s moderation policy for newly created profiles:

  • New profiles created without an institutional email will go through a moderation process that can take up to two weeks.
  • New profiles created with an institutional email will be activated automatically.

Camera Ready Version

Final versions of accepted papers will be given one additional page of content (up to 9 pages for long papers, upto 5 pages for short papers) to address reviewers’ comments. Authors will have the chance to change the submission type from non-archival to archival and vice versa until the camera-ready deadline.

Important Dates

  • Submission Deadline: Monday March 31st, 2025 Wednesday April 2nd, 2025
  • Notification of Acceptance: Monday 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).