---
title: "ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05039v1"
permalink: "https://feed.astralor.com/items/itm_4039b0b01e2836e754df285e"
published: "2026-11-03T15:11:41.000Z"
score: 57
channel: "tech"
tags: ["LLM","AI Agent","OpenAI","Anthropic","Google","RAG","ALBI","LLM-Guided Inductive Logic"]
---

# ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme

## At a glance

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 …

## Key points

- 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 …
- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_4039b0b01e2836e754df285e