Tools

		GeoPAS: Geometric Probing for Algorithm Selection in Continuous Black-Box Optimisation is an algorithm selection system that operates on 2D slices sampled from black-box optimization landscapes. Tool: https://github.com/BradWangW/GeoPAS Report: https://arxiv.org/abs/2604.09095
		MolAS: Molecular Embedding-Based Algorithm Selection in Protein-Ligand Docking is a lightweight docking algorithm selector that predicts per-algorithm performance from pretrained protein-ligand embeddings using an attentional pooling and shallow residual decoder architecture. Tool: https://github.com/BradWangW/MolAS Report: https://arxiv.org/abs/2512.02328               https://link.springer.com/article/10.1186/s13321-026-01168-8
		MC-GNNAS-Dock: Multi-criteria GNN-based Algorithm Selection for Molecular Docking is a molecular docking algorithm selector that improves prediction accuracy by integrating multi-criteria evaluation (RMSD + PoseBusters validity), adding residual connections, and incorporating rank-aware loss functions. Tool: https://github.com/ToothlessOS/MC-GNNAS-Dock Report: https://arxiv.org/abs/2509.26377               https://link.springer.com/chapter/10.1007/978-981-95-7075-1_46
		ALORS: An algorithm recommender system is a collaborative filtering based algorithm selection system. A main contribution of ALORS system is to handle the cold start problem – emitting recommendations for a new problem instance – through the non-linear modeling of the latent factors based on the initial instance representation. Tool: https://www.lri.fr/~sebag/Alors/ Report: http://www.sciencedirect.com/.../article/pii/S0004370216301436
		Automated Algorithm Portfolio DeVISER (ADVISER+) is a web-based system that combines the concepts of algorithm configuration, selection, and portfolio generation. Tool: http://research.larc.smu.edu.sg/adviserplus/ Report: https://mustafamisir.github.io/papers/MIC2017_paper_153.pdf
		Automated Algorithm Portfolio DeVISER (ADVISER) is an earlier version of ADVISER+, purely focusing on algorithm portfolios using non/-parameteric algorithms. Tool: http://research.larc.smu.edu.sg/adviser/ Report: https://mustafamisir.github.io/papers/misir2015ADVISER-LION.pdf
		Generic Intelligent Hyper-heuristic (GIHH) is an award-wining selection hyper-heuristic designed for generality. GIHH is equipped with multiple online adaptive hyper-heuristic procedures and decision mechanisms for simultaneously coordinating them. It is expected to evolve for different search environments without human intervention. Tool: https://code.google.com/archive/p/generic-intelligent-hyper-heuristic/ Report: https://lirias.kuleuven.be/.../358281/3/PhDDissertation-MMISIR.pdf