IJCLR 2026: International Joint Conference on Learning & Reasoning

General Information:

Submissions are invited for the 6th International Joint Conference on Learning and Reasoning to be held at Universitat Politècnica de València, Valencia, Spain, 16-18 September 2026. Since 2021, IJCLR has aimed at being the conference bringing together the international AI community that is interested in the research of integrating learning and reasoning for addressing many of the shortcomings of contemporary AI approaches, including the black-box nature and the brittleness of deep learning, and the difficulty to adapt knowledge representation models in the light of new data.

The authors could submit their papers to the "Main Track" or "Recently Published Papers Track". Selected conference papers from these two tracks are also invited to submit a significantly revised and extended version of their paper to a post-conference special issue of the Machine Learning Journal (please see below).

Submissions are solicited on all aspects of Learning and Reasoning and topics where machine learning is combined with machine reasoning or knowledge representation.

Authors are invited to submit novel, high-quality work that has neither appeared in nor is under consideration for publication by other journals or conferences (except for the Recently Published Papers Track).

Topics of interest for the Journal Track include, but are not limited to:

    Theory & foundations of logical & relational learning.
    Learning in various logical representations and formalisms, such as logic programming & answer set programming, first-order & higher-order logic, description logic & ontologies.
    Inductive methods for program synthesis or example-driven programming.
    Combining logic and functional program induction, meta-interpretative learning & predicate invention.
    Statistical Relational AI, including structure/parameter learning for probabilistic logic languages, relational probabilistic graphical models, kernel-based methods, neural-symbolic learning.
    Systems and techniques that integrate neural, statistical & symbolic learning.
    Systems and techniques addressing aspects of integrating learning, reasoning & optimization.
    Knowledge representation and reasoning in deep neural networks.
    Symbolic knowledge extraction from neural and statistical learning models.
    Neural-symbolic AI.
    Techniques that foster explainability & trustworthiness of AI models, including combinations of machine learning with constraints & satisfiability, explainable AI frameworks and reasoning about the behavior of machine learning models.
    Scaling-up logical & relational learning: parallel & distributed learning techniques, online learning and learning structured representations from data streams.
    Human-Like Computing, including Cognitive and AI aspects of perception, action and learning.