Metraipolis › archive › dc_379eb0dfd74d

FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs — arXiv:2610.33876

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33876
License (as archived): CC0-1.0
Archived: 2026-10-27T08:00:32.600Z
SHA-256 of the archived text: 43a6c97d232e7f18ab6bb38be10820845d122648ffac7677cb4a6a091d6e7f89
Stable URL of this page: https://metraipolis.com/documento/dc_379eb0dfd74d

How to cite

FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs — arXiv:2610.33876 — arXiv (en), https://arxiv.org/abs/2610.33876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_379eb0dfd74d (Metraipolis archive dc_379eb0dfd74d, sha256 43a6c97d232e7f18ab6bb38be10820845d122648ffac7677cb4a6a091d6e7f89)

BibTeX

@misc{dc379eb0dfd74d,
  title = {FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs — arXiv:2610.33876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_379eb0dfd74d; sha256 43a6c97d232e7f18ab6bb38be10820845d122648ffac7677cb4a6a091d6e7f89},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many agent tasks recur with new data or small changes, yet agents regenerate their reasoning and actions on each run, producing different results. Distilling a prior run into a skill helps the agent avoid earlier mistakes, but it still re-runs the full process each time, so runs can vary and incur that cost. We compile a successful agent run into a reusable neuro-symbolic program (NSP) with a set of guidelines we call FlashScript. Actions and data transformations become code, instance-specific values become parameters, and decisions that need model judgment become LLM calls. We identify three layers where these calls belong and three techniques that replace most of them with code. The compilation does not remove nondeterminism; it localizes it, so the deterministic program and its neural calls can be reviewed and tested separately. Across 120 WorkBench analytics tasks with Claude Haiku 4.5, the NSPs were correct and made identical tool calls on every run, using about 70 times fewer input tokens and a third of the runtime of a skill-guided agent whose runs were inconsistent. In a composite version of the tasks, the skill-guided agent's accuracy fell to 23%, and its output inconsistency increased, while the NSPs remained correct and identical across all runs. The NSPs successfully generalized to all 108 unseen instances of the same templates. Our findings suggest that NSPs from agent trajectories can be considered cumulative software assets for end-users to test, maintain, and reuse in their recurring workflows.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.33876 — 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 2026-10-27T07:55:30.860Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).