This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
One Tool Is Enough: Reinforcement Learning for Repository-Level
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LARGER boosts file localization accuracy for repository-level coding agents by integrating lexically anchored graph expansion directly into standard search loops, yielding gains of up to 13.9 points on LocBench.
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.
-
LARGER: Lexically Anchored Repository Graph Exploration and Retrieval
LARGER boosts file localization accuracy for repository-level coding agents by integrating lexically anchored graph expansion directly into standard search loops, yielding gains of up to 13.9 points on LocBench.