1st International Workshop on Advanced Neuro-Symbolic Applications (ANSyA 2025)

Updates here: https://ansya-workshop.github.io/2025/

Workshop at ECAI 2025

Organized by:

• Andrea Agiollo, TU Delft, The Netherlands
• Enkeleda Bardhi, TU Delft, The Netherlands
• Giovanni Ciatto, University of Bologna, Italy
• Sebastijan Dumancic, TU Delft, The Netherlands
• Giuseppe Marra, KU Leuven, Belgium

Aim

The ANSyA workshop aims to advance the practical dimensions of neuro-symbolic AI.

It seeks to bridge the gap between theoretical advancements and industry adoption, showcasing research that addresses real-world problems and delivers actionable solutions.

ANSyA provides a platform for applied neuro-symbolic systems engineering, fostering collaborations between academia and industry, and encouraging innovative thinking.

The workshop aspires to revitalize the applied dimension of neuro-symbolic AI, making it a mainstream paradigm for solving data-driven problems across diverse domains.

Important Dates

• Paper submission deadline: July 14, 2025, AoE

• Author Notification: August 11, 2025, AoE

• Web-site Camera-ready Submission: August 18, 2025, AoE

• Workshop Date: October 25-26 (TBD), 2025, CET

• [Optional] Proceedings Camera-ready Submission: November 9, 2025, AoE

Submission site

https://easychair.org/my/conference?conf=ansya2025

Submission Types

We invite the following types of contribution:

1. full or short papers about NeSy approaches, emphasising practical aspects, applications, or applicability to real-world problems;
   • page limit: 7 pages for full papers, 2 pages for short papers (excluding references);
2. artefact papers presenting software applications tools and libraries with proven potential to impact the NeSy domain;
   • page limit: 2 pages (excluding references);
3. demo papers presenting in detail the usage of software tools which may be relevant in the NeSy domain;
   • page limit: 2 pages (excluding references);
4. dataset description papers presenting the details of datasets that can be used in the NeSy domain;
   • page limit: 2 pages (excluding references);
5. report papers presenting valuable lessons learned in engineering NeSy design and/or applying NeSy to specific fields;
   • page limit: 7 pages (excluding references);
6. position papers concerning NeSy applications in specific fields;
   • page limit: 2 pages (excluding references);
7. survey papers, concerning any of the above.
   • page limit: 7 pages (excluding references).

Preliminary or already-published work can be submitted, provided that the submission is clearly marked as such.

Relevant topics

ANSyA focuses on the practical application of NeSy into any possible field.

Leveraging on the seminal work by Sarker et al., we consider as NeSy any system falling into one (or more) of the following categories:

• neural-based processing systems where input and output are presented in a symbolic form;

• neural-based processing systems that compile symbolic rules during training;

• systems such as Neuro-Symbolic Concept-Learner representing a cascading from neural systems to symbolic reasoners;

• systems such as AlphaGo and AlphaZero where neural pattern recognition subroutines are used within a symbolic problem solver;

• bidirectional framework in which neural and symbolic components communicate, such as DeepProblog and NeurASP;

• systems that embed symbolic reasoning inside a neural engine.

Twin communities

We also welcome contributions from twin communities leveraging different nomenclature for similar concepts, such as informed-machine learning, symbolic knowledge extraction or injection, etc.

Keywords

Given the broad categorization of NeSy AI systems, we welcome papers that propose applications and engineering research in various domains, including (but not limited to):

• NeSy and cybersecurity

• NeSy and intelligent agents

• NeSy and intelligent networked systems

• NeSy in healthcare

• NeSy and large language models

• NeSy in robotics

• NeSy in computer vision

• NeSy for planning

• NeSy for programming (e.g., program synthesis)

• Symbolic knowledge extraction or injection

• Theorem proving via NeSy

• Automated reasoning via NeSy

• AI trustworthiness (explainable, fair, etc.) via NeSy

• Symbolic regression via NeSy

• Inductive logic programming via NeSy

Submission Guidelines

• Submissions should be in ECAI LaTeX format;

• Submissions must be exported in PDF format;

• Camera-ready versions shall include the LaTeX source files;

• Submissions must be anonymised for double-blind review.

Reviewing Format

We consider a 2-phase reviewing process:

1. Each submission will undergo a traditional double-blind review process. This phase applies to all papers, regardless of type, and will determine the final acceptance or rejection decision.

2. The second phase occurs during and after the workshop: accepted contributions are presented (as posters) at the workshop, and authors may collect further comments and insights.

After that, authors who are willing to publish their contribution to the workshop proceedings will be requested to produce a final version of the paper, addressing the reviewers’ suggestions and possibly integrating comments and insights from the workshop.

All papers will undergo the standard assessment in which reviewers will be asked to consider the submission, focusing on its:

• scope: is the paper on-topic w.r.t. the workshop’s track or theme?

• significance: is the idea proposed in the paper meaningful for the NeSy community? Are the results relevant?

• soundness: is the approach proposed in the paper correct and robust? Are experiments (if any) well-designed?

• clarity: is the paper clear and well organized? Is the discussion complete?

• contextualization: is relevant background and related literature being adequately referenced?

• novelty: is the contribution novel either from a conceptual or technical perspective?

• practical applicability: is the proposed idea applicable in practice? Can it scale? Do the authors provide convincing evidence?

Furthermore, the reviews will take into account the specific characteristics of the submitted contributions to obtain their final decision. For example, submissions proposing novel software will receive a score depending also on the quality of the shared software. Similarly, demo papers will receive a score depending on the usability and utility of the tool under demonstration.

Proceedings

The workshop will publish its own proceedings onto Scopus-indexed repositories, such as CEUR-WS.

Accepted papers will be included in the workshop proceedings only if the authors explicitly agree to do so. In this way, works which are not mature enough for publication, as well as works which have already been published elsewhere can be presented and discussed at the workshop.