כתבה
arXiv cs.LG ·
INFUSER: שיפור תהליכי היגיון
INFUSER: Influence-Guided Self-Evolution Improves Reasoning
INFUSER הוא כלי לשיפור תהליכי היגיון. הוא משתמש במודל Qwen ומאפשר שיפור עצמי עם הדרכה מינימלית. INFUSER משתמש בשיטת co-training עם תפקידים משותפים: Generator ו-Solver.
תקציר מקורי באנגליתarXiv:2606.09052v5 Announce Type: replace Abstract: Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision. Yet existing methods either depend on extensively curated or teacher-generated training data, or, when the generator runs unsupervised, reward it by a difficulty heuristic that need not improve the solver. We introduce INFUSER, an iterative co-training framework with two co-evolving roles: a Generator that drafts questions and reference golden answers from a pool of unstructured, automatically collected documents, and a Solver that improves by training on them. The solver is trained with standard correctness rewards against the generator-provided answers, while the generator is rewarded by an opt
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית