Metraipolis › archive › dc_5dc7e49a4cd7

Assessing the Impact of Retrieval-Augmented Generation on Algorithmic Problem-Solving — arXiv:2611.09791

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09791
License (as archived)
CC0-1.0
Archived
2026-11-09T22:34:15.905Z
SHA-256 of the archived text
4e82695022f272fec0e787502a7552329a0c8c50e337632b0d9d0219b998e65d
Stable URL of this page
https://metraipolis.com/documento/dc_5dc7e49a4cd7

How to cite

Assessing the Impact of Retrieval-Augmented Generation on Algorithmic Problem-Solving — arXiv:2611.09791 — arXiv (en), https://arxiv.org/abs/2611.09791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5dc7e49a4cd7 (Metraipolis archive dc_5dc7e49a4cd7, sha256 4e82695022f272fec0e787502a7552329a0c8c50e337632b0d9d0219b998e65d)
BibTeX
@misc{dc5dc7e49a4cd7,
  title = {Assessing the Impact of Retrieval-Augmented Generation on Algorithmic Problem-Solving — arXiv:2611.09791},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09791},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5dc7e49a4cd7; sha256 4e82695022f272fec0e787502a7552329a0c8c50e337632b0d9d0219b998e65d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Competitive programming problems pose distinctive challenges for Large Language Models, as they demand not only proficient code generation but also advanced algorithmic reasoning. This study presents a Retrieval-Augmented Generation approach specifically designed to enhance the capacity of Large Language Models to address such problems. Our approach integrates an embedding-based retrieval mechanism and a similarity search algorithm to identify analogous problems within a knowledge database, employing a dynamically adjusted threshold to mitigate retrieval noise. We conducted an evaluation using the CodeContests dataset, focusing on the test split problems that exhibit similarity to instances from the training split. The experimental framework considered three conditions: (i) problems provided solely with their original descriptions, (ii) problems supplemented with randomly selected examples from the training split, and (iii) problems augmented with similar examples retrieved through the proposed method. In addition, we incorporated a Min-K membership inference analysis to examine whether the generated code solutions were influenced by potential memorization of training data within the evaluated Large Language Models. This complementary perspective enables a deeper understanding of model behavior by distinguishing genuine generalization through retrieval from implicit recall of pretraining samples. Performance was assessed using both pass rates and the CodeForces Elo rating of the problems. The results provide empirical evidence that similarity-based retrieval substantially enhances Large Language Models performance in competitive programming scenarios, offering an scalable framework for improving code generation in algorithmic problem-solving contexts.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2611.09791 — 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 2026-11-09T22:30:47.292Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).