conftrace_

experience-weighted smoothing

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

prompt-level prioritization (1) reward smoothing (1) reinforcement fine-tuning (1) advantage estimation (1) policy optimization (1) sample efficiency (1) reinforcement learning (1)

Papers

PSPO: Prompt-Level Prioritization and Experience-Weighted Smoothing for Efficient Policy Optimization AAAI 2026