Metraipolis › archive › dc_6f2d5fa77613
Competing at Every Price Point with Agentic Evolution over a Menu of LLMs — arXiv:2608.16207
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16207
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:42:47.467Z
- SHA-256 of the archived text
467c798693105456b253ad5790deadb6f18e26083eea3c7f39e12980c92500d6- Stable URL of this page
https://metraipolis.com/documento/dc_6f2d5fa77613
How to cite
Competing at Every Price Point with Agentic Evolution over a Menu of LLMs — arXiv:2608.16207 — arXiv (en), https://arxiv.org/abs/2608.16207 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f2d5fa77613 (Metraipolis archive dc_6f2d5fa77613, sha256 467c798693105456b253ad5790deadb6f18e26083eea3c7f39e12980c92500d6)
BibTeX
@misc{dc6f2d5fa77613,
title = {Competing at Every Price Point with Agentic Evolution over a Menu of LLMs — arXiv:2608.16207},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16207},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f2d5fa77613; sha256 467c798693105456b253ad5790deadb6f18e26083eea3c7f39e12980c92500d6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16207. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Consider a firm that surveys its competition for a particular agentic task and seeks to offer superior accuracy at every price point. A firm that Pareto-dominated its competitors would leave no rational customer a reason to buy elsewhere. This paper shows a path to this kind of capability by evolving multi-LLM Python agents from training pools of at most 100 examples. Given a priced menu of nine LLM endpoints; brief documentation of the task, objective, and API; a simple seed agent; and an operator-chosen per-problem cost target--usually set at an incumbent's own price--RoboPhD, an evolutionary meta-agent, evolves complete agent programs that attack the public frontiers of two semantically dissimilar tasks point by point: DS-1000 (execution-checked code generation) and PaperFindingBench (LLM-judged scientific document retrieval). On public leaderboards for each task, the evolved agents hold every Pareto-frontier slot but one, including Pareto domination of both the top-scoring and the lowest-cost competing points. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16207 — 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 2026-10-18T16:29:13.860Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).