Agents in the Wild Workshop

News

[4/26/2026] Workshop Day is Here — Looking forward to seeing you in Room 204 A/B! Check out our X and LinkedIn posts.
[4/10/2026] Schedule Posted — The final workshop schedule is now available, featuring invited and contributed talks, poster sessions, and a panel discussion.
[4/1/2026] AIWILD @ ICML 2026 — The Second Workshop on Agents in the Wild has been accepted to ICML 2026! See you in Seoul!
[2/9/2026] Deadline Extended — The paper submission deadline has been extended to February 12, 2026 AoE. Also, the deadline to apply to be a reviewer has been extended to February 12, 2026 AoE.
[2/4/2026] Final Call for Papers — The final call for papers is posted! Check out our X and LinkedIn posts.
[2/4/2026] News Coverage — We're excited that the workshop was featured in Agentic AI Weekly!
[2/2/2026] Call for Reviewers — The call for reviewers is posted! Check out our X and LinkedIn posts. We invite researchers to serve as reviewers for the workshop. Prior reviewing experience is helpful but not required; familiarity with workshop topics is expected. Please submit your application by February 9th. We plan to present Best Reviewer Awards!
[1/11/2026] Call for Papers — The call for papers is posted! Check out our X and LinkedIn posts. And the submission portal is now open!
[12/1/2025] Workshop Accepted — The workshop has been accepted by ICLR! See you in Rio!

About

Recent advances in agentic AI have enabled powerful AI systems capable of reasoning, acting, and adapting in diverse real-world environments. However, deploying such "agents in the wild" introduces profound challenges related to safety, security, trustworthiness, and more.

This workshop aims to bring together researchers and practitioners across academia and industry to discuss emerging research directions and practical challenges in developing safe and secure agents. By fostering collaboration across disciplines, the workshop will help chart the next steps toward reliable and trustworthy agent systems that can operate responsibly in open environments.

Call for Papers

The Workshop on Agents in the Wild at ICLR 2026 invites submissions from researchers and practitioners exploring how intelligent agents can reason, act, and adapt safely and securely in open-ended real-world environments.

As agentic AI systems grow more capable, their deployment in dynamic, unpredictable settings introduces challenges in safety, security, and general trustworthiness. This workshop aims to spark discussion across academia and industry on methods, benchmarks, and frameworks for building reliable and trustworthy agents that can operate responsibly "in the wild."

Scope

We welcome contributions on a wide range of topics related to AI agents, including but not limited to:

Agentic safety and alignment
Agent security, privacy, and robustness
Agentic hallucination and factuality
Agentic interpretability and transparency
Agentic fairness and bias
Evaluating and benchmarking agents
Multimodal and computer-use agents
Multi-agent coordination and long-horizon safety
Post-training and adapting agents
Agent systems and infrastructure
Interdisciplinary agentic considerations
Ethics, society, and governing of agents

Important Dates

Paper Submission Open: January 5, 2026 AoE
Paper Submission Deadline: ~~February 5, 2026 AoE~~ February 12, 2026 AoE
Paper Notification Deadline: March 1, 2026 AoE
Camera-ready Version Deadline: April 15, 2026 AoE

Submission Guidelines

Format: This workshop offers two seperate submission tracks:

Regular Papers Track: The workshop welcomes submissions of research and position papers (10 pages). References and supplementary materials will not count against these limits.
Short Papers Track: We encourage submission of short papers (4 pages) to make the workshop more accessible to researchers outside the ML conference publication circuit. These submissions can present implementations of unpublished ideas, modest theoretical results, follow-up experiments, or fresh perspectives on existing work. References and supplementary materials do not count against the 4-page limit.

Since 2025, ICLR has discontinued the separate "Tiny Papers" track, and is instead requiring each workshop to accept short (3–5 pages in ICLR format, exact page length to be determined by each workshop) paper submissions, with an eye towards inclusion; see https://iclr.cc/Conferences/2025/CallForTinyPapers for a history of the ICLR tiny papers initiative. Authors of these papers will be earmarked for potential funding from ICLR, but need to submit a separate application for Financial Assistance that evaluates their eligibility. This application for Financial Assistance to attend ICLR 2026 will become available on https://iclr.cc/Conferences/2026/ at the beginning of February and close early March.

Submission site: Submit papers through the Workshop Submission Portal on OpenReview.

Style file: You must format your submission using the ICLR 2026 LaTeX style file. For convenience, we provide a modified template that refers to our workshop: ICLR 2026 Style Files. Submissions that violate the ICLR style or page limits may be desk-rejected.

Dual-submission policy: The workshop will adopt a non-archival policy, welcoming ongoing and unpublished work, as well as papers under review or recently accepted at other venues (provided they do not breach dual-submission or anonymity policies of the other venue). Workshop submissions can be subsequently or concurrently submitted to other venues.

Visibility: Accepted papers will be made public, but rejected submissions and reviews will not.

Double-blind reviewing: Submissions must be fully anonymized. This policy applies to any supplementary or linked material as well, including code. Any papers found to be in violation of this policy may be desk-rejected.

LLM usage policy: AI-generated papers are not allowed. AI assistance is permitted, but submissions must be primarily human-authored, reflecting original thought and analysis.

Contact: For any questions, please contact us at agentwild-workshop@googlegroups.com.

Schedule

All times are local.

9:00–9:10	Opening Remarks — Dawn Song
9:10–9:40	Invited Talk 1 — Bing Liu From LLMs to Agents: The Evaluation Challenge
9:40–10:10	Invited Talk 2 — Chi Wang Frontiers of Agentic AI
10:10–11:00	Poster Session 1 + Morning Snack Break
11:00–11:30	Invited Talk 3 — Bo Li Guarding the Age of Agents: Advancing Risk Assessment, Guardrails, and Security Certification
11:30–12:00	Invited Talk 4 — Devina Jain Securing Agents in the Wild: Lessons from Large-Scale Attacker-Defender Competitions
12:00–1:00	Lunch Break
1:00–1:45	Panel Discussion The Future of Safe and Secure Agents Moderator: Ruoxi Jia Panelists: Jared Quincy Davis, Devina Jain, Bo Li, Bing Liu, Yizhou Sun
1:45–1:50	Contributed Talk 1 — Ilham Wicaksono Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs
1:50–1:55	Contributed Talk 2 — Weijie Xu Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
1:55–2:00	Contributed Talk 3 — Qiushi Sun OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
2:00–2:30	Invited Talk 5 — Yoshua Bengio Avoiding Uncontrolled Agency with the Scientist AI
2:30–3:00	Invited Talk 6 — Jared Quincy Davis Compound AI Systems: Design Patterns for Secure Multi-Agent Deployments
3:00–3:50	Poster Session 2 + Afternoon Snack Break
3:50–4:20	Invited Talk 7 — Yunyao Li Building & Querying Enterprise Knowledge Bases: From Declarative Languages to Secure Agents
4:20–4:50	Invited Talk 8 — Yizhou Sun ARLArena: Training Framework for Agentic Reinforcement Learning
4:50–5:00	Awards & Closing Remarks — Chenguang Wang