{"type":"link","version":"1.0","title":"Self-Explore to Avoid the Pit: Improving the Reasoning Capabilities of Language Models with Fine-grained Rewards","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2404.10346","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2404.10346.png","thumbnail_width":1200,"thumbnail_height":630}