Metraipolis › archive › dc_86c9d2bbecc3
ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme — arXiv:2611.05039
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05039
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:35:24.540Z
- SHA-256 of the archived text
9b69d742b0237f6d632ef38b469a8f3360e66f86401974235c85d4908e069c77- Stable URL of this page
https://metraipolis.com/documento/dc_86c9d2bbecc3
How to cite
ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme — arXiv:2611.05039 — arXiv (en), https://arxiv.org/abs/2611.05039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86c9d2bbecc3 (Metraipolis archive dc_86c9d2bbecc3, sha256 9b69d742b0237f6d632ef38b469a8f3360e66f86401974235c85d4908e069c77)
BibTeX
@misc{dc86c9d2bbecc3,
title = {ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme — arXiv:2611.05039},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05039},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86c9d2bbecc3; sha256 9b69d742b0237f6d632ef38b469a8f3360e66f86401974235c85d4908e069c77},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce ALBI (Agent for Learning By Induction), a neuro-symbolic ILP framework that replaces the ASP-based hypothesis generator in the Learning from Failures (LFF) paradigm with a Large Language Model (LLM), while retaining SWI-Prolog as a formal verifier. ALBI implements an iterative generate-test-constrain loop: the LLM proposes candidate hypotheses from structured prompts; Prolog tests each candidate; and diagnostic feedback drives refinement. We further introduce semantic anonymization, a metamorphic testing methodology, to distinguish structural symbolic induction from surface-level pattern matching on predicate names. Experiments on 30 standard ILP benchmarks show that ALBI achieves 100% success across three frontier LLMs (Gemini 3.1 Pro, GPT 5.4 Pro, Claude Opus 4.6), matching Popper while requiring only 1.4-1.7 iterations on average. Under anonymization, all models maintain 100% success with a moderate iteration increase (1.36-1.67 times), providing evidence of robust symbolic reasoning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Symbolic Computation (cs.SC). Pagina del lavoro: https://arxiv.org/abs/2611.05039 — 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 2026-11-04T18:32:37.350Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).