AI Paper Atlas

Research map / Large language models / Agents, code and math

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

Timo Pierre Schrader, Lukas Lange, Tobias Kaminski, Simon Razniewski, Annemarie Friedrich

AAAI 2026 · Large language models › Agents, code and math · approach: Code generation benchmarks · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
SFT on solver-filtered chosen ASP encodingsLlama-3.3 70B · LogicPuzzles (two-shot)accuracy (%): 31.0 -> 55.4Improved
add best-of-5 reward-based sampling (no fallbacks) (ablation)Llama-3.3 70B +SFT · LogicPuzzles (two-shot)accuracy (%): 55.4 -> 62.7Improved
add regeneration fallback to best-of-5 (ablation)Llama-3.3 70B +SFT +Seq · LogicPuzzles (two-shot)accuracy (%): 62.7 -> 64.6Improved
add backtracking fallback to best-of-5 (ablation)Llama-3.3 70B +SFT +Seq · LogicPuzzles (two-shot)accuracy (%): 62.7 -> 62.7No clear effect
combine regeneration and backtracking (ablation)Llama-3.3 70B +SFT +Seq · LogicPuzzles (two-shot)accuracy (%): 62.7 -> 66.8Improved
increase best-of-N from 5 to 25 (ablation)Llama-3.3 70B +SFT +TT · LogicPuzzles (two-shot)accuracy (%): 66.8 -> 69.2Improved
apply solver-reward best-of-5 to closed model without fine-tuningGPT-4.1-mini · LogicPuzzles (two-shot)accuracy (%): 39.2 -> 55.4Improved
plug SFT-tuned models into prompt pipelineLlama-3.3 70B · LogicPuzzles (prompt pipeline)accuracy (%): 56.8 -> 78.4 (with TT)Improved
SFT on LogicPuzzles-derived data evaluated on harder GridPuzzles8B models · GridPuzzles (two-shot)accuracy (%): approx. +10pp on averageImproved
use DPO instead of SFT (ablation)ASP instruction tuning · initial experimentsaccuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy