Your Profile Picture

I am a Professor at the Department of Theoretical Informatics of the Institute of Informatics of Federal University of Rio Grande do Sul (UFRGS) in Brazil since 2017. I hold a Ph.D. in Computer Science from the Federal University of Rio Grande do Sul (2016), with a one-year Ph.D. Sandwich at the University of Alberta (UofA), and a Bachelor Degree in Computer Science from the Federal University of Santa Maria (UFSM) (2011).

My doctoral dissertation was awarded the second place in the Doctoral Dissertation Contest of the Brazilian Computer Society (2017) and the first place in the Doctoral Dissertation Contest on Artificial and Computational Intelligence of the Brazilian Conference on Intelligent Systems (2018).

According to A.I. Author Rankings, I am among the top-ranked Brazilian researchers in Core A.I. venues over the past decade.

DBLP ― Google Scholar ― CV Lattes (Portuguese)

E-mail: agpereira@inf.ufrgs.br.
Office: Room 219 - Building 43424 (72) - Campus do Vale.

Research Interests:

  • Artificial Intelligence.
  • Heuristic Search.
  • Classical Planning.
  • Machine Learning.
  • Deep Learning.
  • Large Language Models.
  • Games and Puzzles.
  • Computational Complexity.

Awards:

  • Visiting Professor Award (PRINT), University of Basel (2024).
  • Distinguished Visiting Fellow, Scottish Informatics and Computer Science Alliance (2023).
  • Second place award in the Scientific Initiation Work Contest (Advisor), Brazilian Computer Society (2022).
  • Finalist in the Master Dissertation Contest on Artificial and Computational Intelligence (Advisor), Brazilian Computer Society (2020).
  • First place award in the Scientific Initiation Work Contest (Advisor), Brazilian Computer Society (2018).
  • First place award in the Doctoral Dissertation Contest on Artificial and Computational Intelligence, Brazilian Computer Society (2018).
  • Second place award in the Doctoral Dissertation Contest, Brazilian Computer Society (2017).

Selected Publications:

2025:

  • Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code.
    Augusto B. Corrêa, André G. Pereira, Jendrik Seipp.
    Neural Information Processing Systems (NeurIPS). [Download]
  • Landmark Generation in HTN Planning Revisited.
    Victor S. Putrich, Felipe Meneguzzi, André G. Pereira.
    International Conference on Automated Planning and Scheduling (ICAPS). [Download]

2024:

  • Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planning.
    Rafael V. Bettker, Pedro P. Minini, André G. Pereira, Marcus Ritt.
    Journal of Artificial Intelligence Research (JAIR). [Download]

2023:

  • A Best-First Search Algorithm for FOND Planning and Heuristic Functions to Optimize Decompressed Solution Size.
    Frederico Messa, André G. Pereira.
    International Conference on Automated Planning and Scheduling (ICAPS). [Download]

2022:

  • PEA*+IDA*: An Improved Hybrid Memory-Restricted Algorithm.
    Frederico Messa, André G. Pereira.
    AAAI Conference on Artificial Intelligence (AAAI). [Download]

2021:

  • An LP-Based Approach for Goal Recognition as Planning.
    Luísa R. de A. Santos, Felipe Meneguzzi, Ramon F. Pereira, André G. Pereira.
    AAAI Conference on Artificial Intelligence (AAAI). [Download]

2020:

  • Sequencing Operator Counts with State-Space Search.
    Wesley L. Kaizer, André G. Pereira, Marcus Ritt.
    International Conference on Automated Planning and Scheduling (ICAPS). [Download]

2019:

  • Procedural Generation of Initial States of Sokoban.
    Dâmaris S. Bento, André G. Pereira, Levi H. S. Lelis.
    International Joint Conference on Artificial Intelligence (IJCAI). [Download]
  • Landmark-Enhanced Heuristics for Goal Recognition in Incomplete Domain Models.
    Ramon F. Pereira, André G. Pereira, Felipe Meneguzzi.
    International Conference on Automated Planning and Scheduling (ICAPS). [Download]

2018:

  • Analyzing Tie-Breaking Strategies for the A* Algorithm.
    Augusto B. Corrêa, André G. Pereira, Marcus Ritt.
    International Joint Conference on Artificial Intelligence (IJCAI). [Download]

2017:

  • An approximate nearest neighbors search algorithm for low-dimensional grid locations.
    Adriano Petry, André G. Pereira, Jonas Rodrigues de Souza.
    Earth Science Informatics (ESIN).

2016:

  • Pull and PushPull are PSPACE-complete.
    André G. Pereira, Marcus Ritt, Luciana S. Buriol.
    Theoretical Computer Science (TCS).
  • Improved Heuristic and Tie-Breaking for Optimally Solving Sokoban.
    André G. Pereira, Robert Holte, Jonathan Schaeffer, Luciana S. Buriol, Marcus Ritt.
    International Joint Conference on Artificial Intelligence (IJCAI). [Download]

2015:

  • Optimal Sokoban solving using pattern databases with specific domain knowledge.
    André G. Pereira, Marcus Ritt, Luciana S. Buriol.
    Artificial Intelligence (AIJ).

2013:

  • Finding Optimal Solutions to Sokoban Using Instance Dependent Pattern Databases.
    André G. Pereira, Marcus Ritt, Luciana S. Buriol.
    Symposium on Combinatorial Search (SoCS).

2012:

  • Data assimilation using NeuroEvolution of Augmenting Topologies.
    André G. Pereira, Adriano Petry.
    International Joint Conference on Neural Networks (IJCNN).

Program Committee:

  • ICAPS (2025), AAAI (2023, 2022, 2021, 2020, 2018, 2017), IJCAI (Board PC 2022, SPC 2021, 2019, 2018), SoCS (2021, 2019, 2018).

Current Students:

  • Marco Antonio Chitolina, M.Sc. Student.
    Reducing Test-Time Compute Cost for Large Language Models in Reasoning Domains.

Former Students:

  • Victor Scherer Putrich, M.Sc. Student.
    Landmark Generation in HTN Planning Revisited.
  • Frederico Messa, Ph.D. Student.
    FOND Planning via Explicit Search.
  • Rafael Vales Bettker, M.Sc. Student. Co-Supervisor: Marcus Ritt.
    Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planning.
  • Pedro Probst, M.Sc. Student. Main Supervisor: Marcus Ritt.
    Discovering and Learning Preferred Operators for Classical Planning with Neural Networks.
  • Luísa Rocha de Azevedo Santos, M.Sc. Student.
    LP-Based Approaches for Goal Recognition as Planning.
  • Wesley Luciano Kaizer, M.Sc. Student.
    Sequencing Operator Counts with State-Space Search.
  • Dâmaris da Silva Bento, M.Sc. Student. Main Supervisor: Levi Lelis.
    Procedural Generation of Initial States of Sokoban.
  • Augusto Blaas Corrêa, Scientific Initiation. Co-Supervisor: Marcus Ritt.
    Domain-Dependent Heuristics and Tie-Breakers: Topics in Automated Planning.

Teaching:

  • Inteligência Artificial Avançada (2025/1, 2024/2, 2024/1, 2023/1, 2021/1, 2020/2, 2020/1, 2019/2, 2019/1).
  • Lógica para Computação (2024/2, 2022/2, 2021/2, 2020/2, 2020/1, 2019/2, 2018/2, 2018/1, 2017/1).
  • Algorithms (2024/1, 2023/1, 2022/2, 2021/2, 2021/1, 2019/1).
  • Complexidade de Algoritmos (2025/1, 2023/2, 2017/1).
  • Fundamentos de Algoritmos (2022/1).
  • Teoria dos Grafos e Análise Combinatória (2017/1).