Project description
Explainable, transparent and sustainable automated algorithm design
The complexity of computational problems across scientific and industrial domains has increased the need for automated approaches to algorithm design. In the case of large language models, a new paradigm of automated design of algorithms (ADA) has emerged. It enables direct evolution of algorithm implementations from a broader set of candidate operators and removes the need for handcrafted structures. However, current ADA research focuses mainly on performance, often overlooking trustworthiness, explainability and sustainability, which are just as important. Supported by the Marie Skłodowska-Curie Actions programme, the TSADA project is developing explainable and efficient ADA methods by improving transparency and resource use. It proposes sustainable techniques that reuse prior knowledge to reduce redundant training.
Objective
Algorithms are the key to solving complex problems across diverse research and application domains. However, traditional algorithm design relies heavily on human expertise, making algorithm design a costly and time-consuming process. While recent advances in Algorithm Configuration (AC) have partially automated the design of algorithms, their success still strongly relies on human-crafted algorithmic frameworks, limiting broader adoption across domains. With the advent of Large Language Models (LLMs), a new paradigm for Automated Design of Algorithms (ADA) has emerged, enabling the direct evolution of algorithm implementation from a significantly broader set of candidate operators, eliminating the need for handcrafted frameworks. Despite these advances, current ADA research primarily focuses on achieving competitive performance while neglecting trustworthiness, explainability, and sustainability, which are critical for practical deployment.
This project, TSADA, aims to address these issues by developing methods to enhance the explainability, transparency, and efficiency of ADA, including both traditional AC and LLM-driven approaches. Through working on the design of Satisfiability (SAT) solvers, I will propose sustainable ADA techniques capable of leveraging knowledge of prior algorithms to minimize redundant training tasks. Furthermore, I will systematically compare traditional AC and LLM-driven ADA methodologies to provide evidence-based guidelines for selecting the most suitable approach under different scenarios. By advancing explainable and resource-efficient ADA, TSADA contributes to the broader objectives of Explainable AI and Green AI, paving the way for more trustworthy, transparent, and sustainable algorithmic innovation.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
You need to log in or register to use this function
Keywords
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
-
HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA)
MAIN PROGRAMME
See all projects funded under this programme
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships
See all projects funded under this funding scheme
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
(opens in new window) HORIZON-MSCA-2025-PF
See all projects funded under this callCoordinator
Net EU financial contribution. The sum of money that the participant receives, deducted by the EU contribution to its linked third party. It considers the distribution of the EU financial contribution between direct beneficiaries of the project and other types of participants, like third-party participants.
75006 Paris
France
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.