Results show that the effectiveness of TabPFN is highly problem dependent, and it cannot replace conventional surrogates universally, and it should be adopted selectively according to data availability, landscape complexity, search space characteristics, and its role within the algorithm.
Abstract
Surrogate-assisted evolutionary algorithms (SAEAs) are effective methods for solving expensive optimization problems (EOPs), where surrogate models replace most expensive evaluations and critically influence the final optimization results. In recent years, tabular foundation models have advanced rapidly, and the Tabular Prior-data Fitted Network (TabPFN) has been adopted as a surrogate model for EOPs due to its strong predictive capability, demonstrating promising performance. Motivated by its potential as a surrogate model in SAEAs, this work conducts a comprehensive study that combines extensive experiments with in-depth theoretical analysis to investigate the effectiveness of TabPFN. Specifically, we perform experiments across both offline and online SAEA settings, covering diverse problem scenarios such as single-objective, multi-objective, constrained, combinatorial, mixed-variable, and engineering optimization problems. In addition, we further analyze the advantages and limitations of TabPFN within SAEAs and provide practical guidelines for its application in different optimization settings. Results show that the effectiveness of TabPFN is highly problem dependent, and it cannot replace conventional surrogates universally. Overall, TabPFN should be adopted selectively according to data availability, landscape complexity, search space characteristics, and its role within the algorithm. Customized model management strategies and role-specific algorithm design are necessary to fully exploit its advantages and avoid its pitfalls.
Black-Box Optimization (BBO) is often applied in several engineering fields and can utilize an advancement of numerical measure- ments and simulation technologies. It deals with the optimization func- tions, where an analytical description is unavailable. It relies on meth- ods that require only an input point in the s...
M. I. Zim, Martin Holeňa Czech Academy of Sciences, Institute of Space Science et al.· 0 citations
Surrogate models constitute a promising approach for scaling multi-objective architecture optimization to larger spaces and complex architectural models and maintain the Pareto front quality provided by evolutionary algorithms.
J. A. Díaz-Pace, Daniele Di Pompeo, Antonela Tommasel· 0 citations
The proposed Multi-Objective Narwhal Optimizer (MONO), a Pareto-based extension of the recently developed Narwhal Optimizer, incorporates Pareto dominance, external archive management, adaptive multi-leader guidance, and crowding-distance-based diversity preservation to effectively balance convergence and exploration t...
S. Medjahed, Mourad Bouatouche, Fatima Boukhatem· Journal of Supercomputing· 0 citations
This study reviews and evaluates four widely used MOLP solution approaches and indicates that ASIMOLP consistently achieves the shortest computation times and is therefore the most computationally efficient among the algorithms considered.
P. Nyiam, A. Salhi· Communication in Physical Sc...· 0 citations
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026