y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#puzzle-solving News & Analysis

2 articles tagged with #puzzle-solving. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles
AINeutralarXiv – CS AI · Mar 36/107
🧠

Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning

Researchers introduced Pencil Puzzle Bench, a new framework for evaluating large language model reasoning capabilities using constraint-satisfaction problems. The benchmark tested 51 models across 300 puzzles, revealing significant performance improvements through increased reasoning effort and iterative verification processes.

AIBearisharXiv – CS AI · Mar 36/104
🧠

HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games

Researchers introduced HardcoreLogic, a benchmark of over 5,000 logic puzzles across 10 games to test Large Reasoning Models (LRMs) on non-standard puzzle variants. The study reveals significant performance drops in current LRMs when faced with complex or uncommon puzzle variations, indicating heavy reliance on memorized patterns rather than genuine logical reasoning.