This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
CES applies conditional bidirectional entropy control on top of DAPO to improve accuracy and shorten responses on mathematical benchmarks for 7B and 1.5B LLMs.
RISK introduces a dataset, benchmark, and R1-style RL fine-tuning for GUI agents that achieve 6.8-8.8% offline gains and 70.5% online task success in e-commerce risk management using 7.2% of baseline parameters.
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.
-
Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning
CES applies conditional bidirectional entropy control on top of DAPO to improve accuracy and shorten responses on mathematical benchmarks for 7B and 1.5B LLMs.
-
RISK: A Framework for GUI Agents in E-commerce Risk Management
RISK introduces a dataset, benchmark, and R1-style RL fine-tuning for GUI agents that achieve 6.8-8.8% offline gains and 70.5% online task success in e-commerce risk management using 7.2% of baseline parameters.
- Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation