INFUSER: Influence-Guided Self-Evolution Improves Reasoning
Researchers have developed INFUSER, a novel framework for self-evolving language models that enhances reasoning capabilities. This iterative co-training system features a Generator that creates questions and answers from documents, and a Solver that learns from them. The Generator is rewarded based on an influence score, ensuring it produces questions that genuinely improve the Solver's performance, rather than just difficult ones. INFUSER demonstrated significant improvements, with an 8B model outperforming a larger 32B model on math and coding tasks. AI
IMPACT Enhances LLM reasoning capabilities by creating adaptive training curricula, potentially leading to more capable AI agents.