method · first seen 7 Oct 2026
reinforcement learning from fine-tuning
Also: post-training with reinforcement learning
Applying reinforcement learning after supervised fine-tuning to improve a language model's decisions on a task.
Mentions per week
PapersCodeDiscussion
Earliest sources
- SOTA: Stock Options Trading Agents Guided by Option-Implied Return DistributionsPapers · 7 Oct 2026 · Yizhen Xie, Mengyang Liu
Latest sources
- SOTA: Stock Options Trading Agents Guided by Option-Implied Return DistributionsPapers · 7 Oct 2026 · Yizhen Xie, Mengyang Liu