Researchers propose Intervened Preference Optimization (IPO) to address safety issues in Large Reasoning Models, where chain-of-thought reasoning contains harmful content even when final responses appear safe. The method achieves over 30% reduction in harmfulness while maintaining reasoning performance.
Researchers introduced AgentMath, a new AI framework that combines language models with code interpreters to solve complex mathematical problems more efficiently than current Large Reasoning Models. The system achieves state-of-the-art performance on mathematical competition benchmarks, with AgentMath-30B-A3B reaching 90.6% accuracy on AIME24 while remaining competitive with much larger models like OpenAI-o3.
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.
