method · first seen 15 Oct 2026
policy optimization
Also: PO
Reinforcement-style training that updates a generative model's policy using reward or advantage signals.
Mentions per week
PapersCodeDiscussion
Earliest sources
- P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document ParsingPapers · 15 Oct 2026 · Yong Zu, Ninghua Yang, Zezhong Tan, Xinhong Ma, Ziqiang Dong, Yang Yang
- One Act, Many Masks: Effect-Marginal Policy Optimization for Long-Horizon AgentsPapers · 21 Oct 2026 · Shaojin Ma, Ruitao Wang, Pengyi Li, Jie Yang, Liangyu Chen, Gangyi Zhao, Hongyao…
- Learning Multi-Agent Orchestration:Higher-Order Interactions in Policy ImprovementPapers · 5 Nov 2026 · Kaixuan Liu, Guojun Xiong
- Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPsPapers · 12 Nov 2026 · Ofir Schlisselberg, Alon Cohen, Yishay Mansour
Latest sources
- Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPsPapers · 12 Nov 2026 · Ofir Schlisselberg, Alon Cohen, Yishay Mansour
- Learning Multi-Agent Orchestration:Higher-Order Interactions in Policy ImprovementPapers · 5 Nov 2026 · Kaixuan Liu, Guojun Xiong
- One Act, Many Masks: Effect-Marginal Policy Optimization for Long-Horizon AgentsPapers · 21 Oct 2026 · Shaojin Ma, Ruitao Wang, Pengyi Li, Jie Yang, Liangyu Chen, Gangyi Zhao, Hongyao…
- P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document ParsingPapers · 15 Oct 2026 · Yong Zu, Ninghua Yang, Zezhong Tan, Xinhong Ma, Ziqiang Dong, Yang Yang