This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
arXiv preprint arXiv:2509.09284 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
APPS approximates power targets p(x)^alpha via parallel particle propagation with proposal-corrected reweighting and future-value-guided selection at block boundaries, improving accuracy-runtime trade-offs in training-free decoding.
T-STAR consolidates multi-turn trajectories into a Cognitive Tree for variance-reduced step-level advantages and surgical policy optimization via thought grafting at critical points.
citing papers explorer
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
APPS approximates power targets p(x)^alpha via parallel particle propagation with proposal-corrected reweighting and future-value-guided selection at block boundaries, improving accuracy-runtime trade-offs in training-free decoding.
-
Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
T-STAR consolidates multi-turn trajectories into a Cognitive Tree for variance-reduced step-level advantages and surgical policy optimization via thought grafting at critical points.