Metraipolis › archive › dc_3ada2f115f85
Robustness Starts with the Objective: Designing and Certifying Robust LLM-Generated Heuristics — arXiv:2611.00504
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00504
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:30:51.355Z
- SHA-256 of the archived text
3ed74d154014a6e1e8391df047b411b51f76301b1a36d3792f80442f69e100f7- Stable URL of this page
https://metraipolis.com/documento/dc_3ada2f115f85
How to cite
Robustness Starts with the Objective: Designing and Certifying Robust LLM-Generated Heuristics — arXiv:2611.00504 — arXiv (en), https://arxiv.org/abs/2611.00504 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ada2f115f85 (Metraipolis archive dc_3ada2f115f85, sha256 3ed74d154014a6e1e8391df047b411b51f76301b1a36d3792f80442f69e100f7)
BibTeX
@misc{dc3ada2f115f85,
title = {Robustness Starts with the Objective: Designing and Certifying Robust LLM-Generated Heuristics — arXiv:2611.00504},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00504},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ada2f115f85; sha256 3ed74d154014a6e1e8391df047b411b51f76301b1a36d3792f80442f69e100f7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00504. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLMs are increasingly used to design heuristics for computer systems. However, most synthesis frameworks evaluate candidates by their average performance, which can mask severe regressions on specific workloads. Even adding adversarial training inputs doesn't eliminate these regressions, and percentile objectives (e.g., optimizing for the 95th percentile) overlook how severe regressions can be beyond the selected threshold. We present TAILOR, a framework that guides LLM synthesis using the Conditional Value at Risk (CVaR) of the cost difference between each candidate and an existing baseline on the same workload. This paired CVaR measures the average difference over the worst fraction of workloads. We show that a negative paired CVaR guarantees improvements in both average performance and tail optimality gap relative to the unknown optimum, without ever computing that optimum. We find that TAILOR achieves the best mean--tail trade-off among the synthesis objectives we evaluate across three case studies: Azure GPU batch admission, Azure VM packing, and server placement. Tested across seven diverse optimization benchmarks, TAILOR produces heuristics that are certified with 99% confidence to improve both average performance and tail optimality gaps over the baseline in six of them. On these six benchmarks, TAILOR also outperforms known robust, human-designed alternatives in the tail while achieving better or comparable average-performance improvement over the baseline. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Distributed, Parallel, and Cluster Computing (cs.DC); Performance (cs.PF). Pagina del lavoro: https://arxiv.org/abs/2611.00504 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:29:48.451Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).