{"paper":{"title":"Better Together, in the Right Order: Classical-then-LLM Optimization for SE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Srinath Srinivasan, Tim Menzies","submitted_at":"2026-07-01T02:32:14Z","abstract_excerpt":"A growing body of work combines large language models (LLMs) with classical optimizers for software engineering (SE) configuration tasks. Often, the classical optimizer is in charge: it owns the search loop and calls the LLM only to assist in subroutines (e.g. to warm-start the first generation, propose a mutation, or stand in as a surrogate). We report that there is much value in the reverse approach: seeding an LLM with the results from a cheap classical learner.\n  We call this method SNAP2. Applied to over 100 SE tasks, it is the single best of all methods studied, reaching the top tier on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02583","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.02583/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}