Projects

About

CodeEvolve is an open-source framework that combines large language models (LLMs) with evolutionary search to synthesize high-performing algorithmic solutions. CodeEvolve couples an islands-based genetic algorithm with modular LLM orchestration, using execution feedback and task-specific metrics to guide selection and variation.

Exploration and exploitation are balanced through context-aware recombination, adaptive meta-prompting, and targeted refinement of promising solutions. We evaluate CodeEvolve on benchmarks used to assess Google DeepMind’s AlphaEvolve and include direct comparisons with popular open-source frameworks for algorithmic discovery and heuristic design.

Our results show that CodeEvolve achieves state-of-the-art (SOTA) performance on several tasks, with open-weight models often matching or exceeding closed-source baselines at a fraction of the compute cost.

About

Inter Quantum Ready is a multi-initiative research project whose primary goal is to explore the potential of quantum paradigms to solve complex, high-dimensional problems that are challenging for classical systems — while simultaneously strengthening the relationship between public research institutions and industry, fostering the development of researchers who can be absorbed by the private sector.

The project also aims to elevate Inter’s maturity in quantum technologies, both to increase resilience against cybersecurity threats and to develop new algorithms with disruptive potential in the financial sector.

Research Context

Quantum computing has shown promise across a wide range of applications, including optimization, information security, and financial modeling. With the rise of quantum computers capable of Quantum Error Correction (QEC), these paradigms are expected to become increasingly relevant in the near future.

Within Inter Quantum Ready, specific sub-projects are defined by concrete research problems that can generate scientific publications, patents, or prototype implementations.

UFMG Partnership

At the heart of this initiative is a research partnership with the Department of Computer Science (DCC) of UFMG — the best computer science research center in Brazil and one of the top 200 in the world — under the program “Paradigmas quânticos e potenciais aplicações ao mercado financeiro” (Quantum Paradigms and Potential Applications to the Financial Market).

This partnership, announced in March 2025, funds research in quantum computing, quantum information, and quantum communication, guided by strategic demands at Inter. It involves faculty and students from both DCC and UFMG’s Department of Physics (DF), supported by Inter Science specialists led by Bruno Grossi.

Active Research Lines

• Hardware-Efficient QAOA for combinatorial optimization in finance (index tracking, portfolio optimization)
• Quantum Machine Learning for fraud detection, credit scoring, and anomaly detection
• Quantum Information Theory — contextuality and graph-theoretic foundations
• Quantum-classical hybrid models for high-dimensional financial problems on NISQ devices

Publications

See the publications page for papers produced under this initiative, including work presented at the VIII WECIQ|WCQ (2026).