Metraipolis › archive › dc_dcdd92cff92f

Reasoning Patterns for Efficient AI Coding: An Empirical Study — arXiv:2610.34943

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.34943
License (as archived): CC0-1.0
Archived: 2026-10-27T08:02:24.078Z
SHA-256 of the archived text: 550e0594a8ef5e83f63ad944b9d690eb1e408cc35494f0c5eccbd489bbea8375
Stable URL of this page: https://metraipolis.com/documento/dc_dcdd92cff92f

How to cite

Reasoning Patterns for Efficient AI Coding: An Empirical Study — arXiv:2610.34943 — arXiv (en), https://arxiv.org/abs/2610.34943 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcdd92cff92f (Metraipolis archive dc_dcdd92cff92f, sha256 550e0594a8ef5e83f63ad944b9d690eb1e408cc35494f0c5eccbd489bbea8375)

BibTeX

@misc{dcdcdd92cff92f,
  title = {Reasoning Patterns for Efficient AI Coding: An Empirical Study — arXiv:2610.34943},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34943},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcdd92cff92f; sha256 550e0594a8ef5e83f63ad944b9d690eb1e408cc35494f0c5eccbd489bbea8375},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34943. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Reasoning Models (LRMs) generate long reasoning traces that expose intermediate inference behavior, offering opportunities to study and control reasoning in AI coding. However, the underlying patterns in these traces and their potential for analyzing and guiding coding models remain poorly understood, limiting systematic characterization and inference-time control of LRM reasoning. We conduct an empirical study of reasoning patterns across four representative coding tasks. We transform reasoning traces into structured action sequences and mine recurring fragments using within-task support, cross-task contrasts, and valid--invalid support contrasts. We characterize four general reasoning patterns by coding agents: design-to-implementation for code generation, state tracing for execution reasoning, evidence--fix--recheck for debugging, and semantic mapping for translation. We further identify positive and negative patterns associated with valid and invalid reasoning traces, respectively. Positive patterns reflect verification-driven convergence, whereas negative patterns reflect repeated design revision, reflection, and knowledge recall without closure. To demonstrate their practical utility, we evaluate three pattern-based applications: task identification, pattern-guided prompting, and pattern-aware early stopping. Features capturing general reasoning patterns enable accurate task identification from reasoning traces without accessing task descriptions or final answers. Prompting guided by positive and negative patterns improves the overall accuracy of downstream tasks, while negative pattern-aware early stopping substantially reduces API-reported token usage with only a modest decrease in pass@1. All three applications also generalize to previously unseen models, showing that reasoning patterns can support both the analysis and control of LRM behavior in AI coding.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.34943 — 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 2026-10-27T07:55:30.951Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).