Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence
[Sztuczna inteligencja] Autorzy: Zhiqin Yang, Jingwen Fu, Yuhan Liu i 16 więcej
Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress to open-ended and agentic tasks remains difficult because reliable rewards are harder to obtain and direct human supervision cannot keep pace with the scale and complexity of model-generated experience. This paper studies how LRMs can continue to improve as human supervision gradually recedes from the learning loop. We examine two connected dimensions of this problem. The reward axis traces the development from per-instance human judgments to reusable verifiers and rewards that operate even without human feedback. The experience axis examines how learning can progress from human-curated tasks and environments toward self-generated curricula, …
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja