A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving

• URL: http://arxiv.org/abs/2512.17093v1
• Date: Thu, 18 Dec 2025 21:45:45 GMT
• Title: A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving
• Abstract summary: We introduce a novel ASP-solver-in-the-loop approach for solver-guided instruction-tuning of large language models (LLMs)<n>Our method only requires problem specifications in natural language and their solutions.<n>We apply supervised fine-tuning to train LLMs on curated data and further improve robustness using a solver-guided search.
• Score: 14.391923692962754
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The rise of large language models (LLMs) has sparked interest in coding assistants. While general-purpose programming languages are well supported, generating code for domain-specific languages remains a challenging problem for LLMs. In this paper, we focus on the LLM-based generation of code for Answer Set Programming (ASP), a particularly effective approach for finding solutions to combinatorial search problems. The effectiveness of LLMs in ASP code generation is currently hindered by the limited number of examples seen during their initial pre-training phase. In this paper, we introduce a novel ASP-solver-in-the-loop approach for solver-guided instruction-tuning of LLMs to addressing the highly complex semantic parsing task inherent in ASP code generation. Our method only requires problem specifications in natural language and their solutions. Specifically, we sample ASP statements for program continuations from LLMs for unriddling logic puzzles. Leveraging the special property of declarative ASP programming that partial encodings increasingly narrow down the solution space, we categorize them into chosen and rejected instances based on solver feedback. We then apply supervised fine-tuning to train LLMs on the curated data and further improve robustness using a solver-guided search that includes best-of-N sampling. Our experiments demonstrate consistent improvements in two distinct prompting settings on two datasets.

Related papers

• Logic-Guided Data Extraction with Answer Set Programming and Large Language Models [0.7874708385247353]
  This paper proposes a logic-guided data extraction framework combining Large Language Models (LLMs) with Answer Set Programming (ASP)<n>The proposed approach uses ASP reasoning to identify which predicates are logically admissible at each stage and to guide extraction queries.<n> Experiments on ASP-derived benchmarks show that the framework reduces LLM calls and improves extraction quality by mitigating spurious outputs.
  arXiv  Detail & Related papers  (2026-06-08T15:53:28Z)
• Constraint-aware Path Planning from Natural Language Instructions Using Large Language Models [1.4180331276028664]
  We propose a flexible framework to solve constrained path planning problems directly from natural language input.<n>The core idea is to allow users to describe routing tasks conversationally, while enabling the LLM to interpret and solve the problem.<n>This method provides a scalable and generalizable approach for solving real-world routing tasks with minimal human intervention.
  arXiv  Detail & Related papers  (2026-02-26T09:01:42Z)
• Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language [67.51318974970985]
  Solving puzzles in natural language poses a long-standing challenge in AI.<n>We propose Logic-of-Thought, a framework that bridges large language models with logic programming.<n>We evaluate our method on various grid puzzles and dynamic puzzles involving actions, demonstrating near-perfect accuracy across all tasks.
  arXiv  Detail & Related papers  (2025-05-22T01:37:40Z)
• Interactive and Expressive Code-Augmented Planning with Large Language Models [62.799579304821826]
  Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. We propose REPL-Plan, an LLM planning approach that is fully code-expressive and dynamic.
  arXiv  Detail & Related papers  (2024-11-21T04:23:17Z)
• Capturing Sparks of Abstraction for the ARC Challenge [0.10878040851637999]
  Even commercial Large Language Models (LLMs) struggle to 'understand' many of the problems. We demonstrate that 'Sparks of Abstraction' can be extracted from the LLM output. Both the arc-dsl-llm DSL framework and the Gemini LLM-generated data are made Open Source.
  arXiv  Detail & Related papers  (2024-11-17T23:40:00Z)
• Crystal: Illuminating LLM Abilities on Language and Code [58.5467653736537]
  We propose a pretraining strategy to enhance the integration of natural language and coding capabilities. The resulting model, Crystal, demonstrates remarkable capabilities in both domains.
  arXiv  Detail & Related papers  (2024-11-06T10:28:46Z)
• Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting [22.025533583703126]
  We propose a novel Prompt Recursive Search (PRS) framework for large language models (LLMs) PRS framework incorporates an assessment of problem complexity and an adjustable structure, ensuring a reduction in the likelihood of errors. Compared to the Chain of Thought (CoT) method, the PRS method has increased the accuracy on the BBH dataset by 8% using Llama3-7B model, achieving a 22% improvement.
  arXiv  Detail & Related papers  (2024-08-02T17:59:42Z)
• Thought of Search: Planning with Language Models Through The Lens of Efficiency [22.47015814897628]
  We argue that recent trends abandon both soundness and completeness for the sake of inefficiency. We show that by using LLMs to produce the code for the search components we can solve the entire datasets with 100% accuracy.
  arXiv  Detail & Related papers  (2024-04-18T01:27:29Z)
• Benchmarking the Text-to-SQL Capability of Large Language Models: A Comprehensive Evaluation [33.41556606816004]
  Large Language Models (LLMs) have emerged as a powerful tool in advancing the Text-to- task. There is still no consensus on the optimal prompt templates and design frameworks. Existing benchmarks inadequately explore the performance of LLMs across the various sub-tasks of the Text-to- process.
  arXiv  Detail & Related papers  (2024-03-05T13:23:48Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying [71.86163159193327]
  Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. We introduce LaGR, which uses this predictive ability of LLMs to propose solutions to tasks that have been partially completed by a primary reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2023-08-21T02:07:35Z)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback [127.75419038610455]
  Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
  arXiv  Detail & Related papers  (2023-02-24T18:48:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.