Algorithm Selection with Zero Domain Knowledge via Text Embeddings

Computer Science > Artificial Intelligence [Submitted on 20 Mar 2026] Algorithm Selection with Zero Domain Knowledge via Text Embeddings Stefan Szeider We propose a feature-free approach to algorithm selection that replaces hand-crafted instance features with pretrained text embeddings. Our method, ZeroFolio, proceeds in three steps: it reads the raw instance file as plain text, embeds it with a pretrained embedding model, and selects an algorithm via weighted k-nearest neighbors. The key to our approach is the observation that pretrained embeddings produce representations that distinguish problem instances without any domain knowledge or task-specific training. This allows us to apply the same three-step pipeline (serialize, embed, select) across diverse problem domains with text-based instance formats. We evaluate our approach on 11 ASlib scenarios spanning 7 domains (SAT, MaxSAT, QBF, ASP, CSP, MIP, and graph problems). Our experiments show that this approach outperforms a random forest trained on hand-crafted features in 10 of 11 scenarios with a single fixed configuration, and in all 11 with two-seed voting; the margin is often substantial. Our ablation study shows that inverse-distance weighting, line shuffling, and Manhattan distance are the key design choices. On scenarios where both selectors are competitive, combining embeddings with hand-crafted features via soft voting yields further improvements. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2604.19753 [cs.AI]   (or arXiv:2604.19753v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.19753 Focus to learn more Submission history From: Stefan Szeider [view email] [v1] Fri, 20 Mar 2026 13:07:59 UTC (299 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CL cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)