# ADVENT: LLM-Driven Automatic Predicate Invention for ILP

arXiv: https://arxiv.org/abs/2607.01585 · HTML: https://mlsanity.com/paper/2607.01585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Inductive logic programming at 30: a new introduction](https://mlsanity.com/paper/2008.07912/) (2020)
- [Learning programs by learning from failures](https://mlsanity.com/paper/2005.02259/) (2020)
- [Clover: Closed-Loop Verifiable Code Generation](https://mlsanity.com/paper/2310.17807/) (2023)
- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning](https://mlsanity.com/paper/2601.20055/) (2026)
- [Forgetting to learn logic programs](https://mlsanity.com/paper/1911.06643/) (2019)
- [Inductive Learning of Logical Theories with LLMs: An Expressivity-Graded Analysis](https://mlsanity.com/paper/2408.16779/) (2024)
- [From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models](https://mlsanity.com/paper/2505.21935/) (2025)
- [Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models](https://mlsanity.com/paper/2509.21874/) (2025)
- [Hypothesis Generation via LLM-Automated Language Bias for ILP](https://mlsanity.com/paper/2505.21486/) (2025)
- [Predicate Renaming via Large Language Models](https://mlsanity.com/paper/2510.25517/) (2025)

## Abstract (arXiv)

Predicate invention (PI), the creation of new predicates to extend the hypothesis space, remains a critical bottleneck in Inductive Logic Programming (ILP). Existing methods rely on domain expertise and produce semantically opaque predicates, hindering adaptation to unfamiliar domains and cross-task reuse. We present ADVENT, an LLM-driven PI mechanism for ILP. ADVENT pairs LLM abductive generation with Prolog deductive verification, forming an iterative loop in which concrete execution results guide the LLM to refine candidate predicates. The mechanism leverages Large Language Models to identify implicit patterns in structured relational data and invent auxiliary predicates with meaningful names and definitions. Invented predicates and learned rules accumulate in a knowledge pool for cross-task reuse. Experiments on nine poker-hand concepts across seven LLMs show that LLM-driven PI achieves 58% success rate where ILP alone fails entirely, formal verification raises this to 80%, and the knowledge pool yields gains up to +31 percentage points, while producing human-interpretable rules. These results suggest that ADVENT offers a promising direction for automating predicate invention and enabling cross-task knowledge reuse in ILP.