Embedded Files
Algorithmic Fairness Across Alignment Procedures
April 26 or 27, 2026 - Rio de Janeiro, Brazil
Pre-Registration Form: https://forms.gle/hShPK8KqhJ2mQ7RJ7
The Algorithmic Fairness Across Alignment Procedures and Agentic Systems (AFAA) workshop aims to spark
discussions on rethinking fairness in AI alignment procedures and agentic system development.
The Algorithmic Fairness Across Alignment Procedures and Agentic Systems (AFAA) workshop aims to spark
discussions on rethinking fairness in AI alignment procedures and agentic system development.
AI has transitioned from predictive models to interactive, autonomous agents capable of reasoning, planning, and executing complex goals. As the systems increasingly influence social, economic, and scientific decisions, they determine whose interests are represented and whose opportunities are constrained. Ensuring fairness, therefore, is no longer an ethical preference but a practical imperative.
AI systems are no longer limited to making isolated predictions. They now reason, interact, and generate content across text, images, and other modalities. As a result, the fairness challenges they pose have fundamentally transformed. Traditional fairness frameworks, developed primarily for prediction and/or prediction-based decision-making (e.g., classification, regression, clustering tasks) no longer suffice. The canonical algorithmic fairness focus is increasingly inadequate for addressing the procedural, temporal, and emergent fairness issues that arise with advanced AI systems.
In particular, the AI community faces an urgent question:
How do fairness principles/tools evolve when AI systems not only predict, but also adapt and act?
This workshop, Algorithmic Fairness Across Alignment Procedures and Agentic Systems (AFAA), emerges at this pivotal moment as a timely forum for rethinking fairness in AI alignment processes and agentic system development. By examining fairness across alignment procedures and agentic systems, this workshop creates a crucial forum for bridging the gap between rapid technical advances in model capabilities and the equally important advances needed in frameworks of algorithmic fairness to govern these powerful systems.
Call for Papers
Call for Papers
We invite submissions to the ICLR 2026 Workshop on Algorithmic Fairness Across Alignment Procedures and Agentic Systems (AFAA) (https://openreview.net/group?id=ICLR.cc/2026/Workshop/AFAA). This workshop explores how fairness principles and tools must evolve as AI systems increasingly reason, adapt, and act autonomously. In particular, we examine how alignment procedures and agentic systems shape downstream behavior (e.g., agents/applications based on foundation models) and their societal impacts. Our workshop aims to actively engage with these intersections, attracting researchers from computer science, philosophy, law, and social sciences due to its theoretical and practical implications.
We invite submissions to the ICLR 2026 Workshop on Algorithmic Fairness Across Alignment Procedures and Agentic Systems (AFAA) (https://openreview.net/group?id=ICLR.cc/2026/Workshop/AFAA). This workshop explores how fairness principles and tools must evolve as AI systems increasingly reason, adapt, and act autonomously. In particular, we examine how alignment procedures and agentic systems shape downstream behavior (e.g., agents/applications based on foundation models) and their societal impacts. Our workshop aims to actively engage with these intersections, attracting researchers from computer science, philosophy, law, and social sciences due to its theoretical and practical implications.
We welcome submissions of novel work relating to fairness in alignment procedures, agentic AI systems, and foundation models in general, including (but not limited to):
We welcome submissions of novel work relating to fairness in alignment procedures, agentic AI systems, and foundation models in general, including (but not limited to):
- Normative foundations of alignment and fairness
- Fairness-aware value learning and preference modeling
- Cultural and contextual dimensions of alignment
- Governance and oversight for agentic systems
- Ethical and accountability frameworks
- Long-term fairness and societal impact
- Fairness metrics and evaluation for agentic AI
- Bias mitigation in foundation models
- Trade-offs between fairness, alignment, and performance
We also continue to accept broad work on fairness including, fairness metrics and mitigation techniques, novel formalizations of fairness, algorithmic approaches to capturing and mitigating evolving biases, and methods in fairness related subfields (model multiplicity, interpretability, robustness, etc.)
We also continue to accept broad work on fairness including, fairness metrics and mitigation techniques, novel formalizations of fairness, algorithmic approaches to capturing and mitigating evolving biases, and methods in fairness related subfields (model multiplicity, interpretability, robustness, etc.)
The workshop will include two tracks: a Main Papers Track, and a Tiny/Short Papers Track.
The workshop will include two tracks: a Main Papers Track, and a Tiny/Short Papers Track.
Submission platform: OpenReview
Template: ICLR 2026 template must be used. Similar to ICLR, the AFAA workshop is double blind. Related arXiv papers by the same authors do not break anonymity; if cited, these should be cited in third person.
Deadlines (for both tracks):
Deadlines (for both tracks):
Full Submission: Jan 31, 2026 AoE
Full Submission: Jan 31, 2026 AoE
Acceptance Notification: Mar 01, 2026 AoE
Acceptance Notification: Mar 01, 2026 AoE
Dual-submission policy: We accept submissions of ongoing unpublished work as well as work submitted elsewhere (FAccT, ICML, SaTML, etc). We also welcome substantial extensions of works previously presented at non-archival venues. However, we do not accept work that has already been published in a journal or included in conference proceedings (including the ICLR main conference).
Dual-submission policy: We accept submissions of ongoing unpublished work as well as work submitted elsewhere (FAccT, ICML, SaTML, etc). We also welcome substantial extensions of works previously presented at non-archival venues. However, we do not accept work that has already been published in a journal or included in conference proceedings (including the ICLR main conference).
LLM usage policy: Authors must follow ICLR 2026 policies on Large Language Model usage: https://blog.iclr.cc/2025/08/26/policies-on-large-language-model-usage-at-iclr-2026/
LLM usage policy: Authors must follow ICLR 2026 policies on Large Language Model usage: https://blog.iclr.cc/2025/08/26/policies-on-large-language-model-usage-at-iclr-2026/
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. For AFAA, we will accept these submissions through our Tiny/Short Papers Track (up to 3 pages in ICLR format).
Main Papers Track
Main Papers Track
(6-9 pages)
not including references and appendix
(6-9 pages)
not including references and appendix
The Main Papers Track serves to highlight novel contributions in full paper length.
The Main Papers Track serves to highlight novel contributions in full paper length.
Accepted papers will be presented as spotlight talks or posters. Selected papers may be included in PMLR workshop proceedings upon author opt-in after acceptance, pending final editorial review.
Accepted papers will be presented as spotlight talks or posters. Selected papers may be included in PMLR workshop proceedings upon author opt-in after acceptance, pending final editorial review.
Tiny/Short Papers Track
Tiny/Short Papers Track
(up to 3 pages)
not including references and appendix
(up to 3 pages)
not including references and appendix
This track encourages early-stage or emerging research.
This track encourages early-stage or emerging research.
This track particularly welcomes submissions from budding researchers and new contributors to the ML conference community. Accepted tiny/short papers will be presented as posters.
This track particularly welcomes submissions from budding researchers and new contributors to the ML conference community. Accepted tiny/short papers will be presented as posters.
Invited Speakers
Invited Speakers
TBA
TBA
Panel
Panel
TBA
TBA
Roundtable Leads
Roundtable Leads
TBA
TBA
Core Organizing Members
Core Organizing Members
(Meta)
(Meta)
Advisory Members
Advisory Members
Code of Conduct
Code of Conduct
Reviewer Volunteer Form
If you would like to help as a reviewer, please fill out the form below.
Reviewer Volunteer Form
If you would like to help as a reviewer, please fill out the form below.
Page updated
Google Sites
Report abuse