This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
Synthrl: Scalingvisualreasoning with verifiable data synthesis
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.
GaMMA unifies global and temporal music understanding in a single LMM via MoE audio encoders and progressive training, achieving new state-of-the-art accuracies on music benchmarks including 79.1% on MuchoMusic.
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.
-
SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.
-
GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models
GaMMA unifies global and temporal music understanding in a single LMM via MoE audio encoders and progressive training, achieving new state-of-the-art accuracies on music benchmarks including 79.1% on MuchoMusic.