It is found that neutral framing of behavioural features, reporting the feature value without prescriptive advice, consistently outperforms the prescriptive variants, and that prescriptive feedback steers the median feature value in the advised direction in only 37% of cases despite empirically grounded advice.
A hybrid nested search is formalized, in which an outer loop has the LLM propose a structural sketch, with numeric gaps, and an inner numerical optimizer tunes the sketch.
Findings indicate that while LLM-based performance prediction is not yet a reliable substitute for benchmarking, it shows potential as a complementary pre-screening tool in iterative algorithm design, particularly in settings where code modifications follow predictable patterns.
Michal Pluháček, Paweł Kolendo, Krzysztof Tylka-Suleja et al.· GECCO Companion· 0 citations
Combinatorial problems appear in numerous industrial applications. A common approach is to formulate these problems as declarative constraint models that can subsequently be compiled to and solved by a range of back-end solvers. Recent work shows that Large Language Models (LLMs) can produce correct models from natural...
Analysis shows that many generated operators use semantics to guide selection, suggesting that LLMs can produce non-trivial search heuristics from the task description alone, and the relationship between public LLM leaderboard rankings and GP performance is examined.
Overall, statistic synthesis is much easier than map synthesis, some collections remain near-zero, long prompts cause a sharp accuracy cliff, and exact symbolic rule induction remains brittle.
Soham Dan· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
