This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
Think only when you need with large hybrid-reasoning models.arXiv preprint arXiv:2505.14631
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
TIME trains LLMs to trigger compact, context-triggered reasoning via time tags and tick events, improving TIMEBench scores while cutting explicit reasoning tokens by an order of magnitude.
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
HiRO-Nav adaptively triggers reasoning only on high-entropy actions via a hybrid training pipeline and shows better success-token trade-offs than always-reason or never-reason baselines on the CHORES-S benchmark.
EviOmni unifies evidence reasoning and extraction in a single RL trajectory with token masking and verifiable rewards for answer, length, and format to produce compact high-quality evidence for RAG.
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gains across 15 benchmarks.
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.
-
TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning
TIME trains LLMs to trigger compact, context-triggered reasoning via time tags and tick events, improving TIMEBench scores while cutting explicit reasoning tokens by an order of magnitude.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
HiRO-Nav adaptively triggers reasoning only on high-entropy actions via a hybrid training pipeline and shows better success-token trade-offs than always-reason or never-reason baselines on the CHORES-S benchmark.
-
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
EviOmni unifies evidence reasoning and extraction in a single RL trajectory with token masking and verifiable rewards for answer, length, and format to produce compact high-quality evidence for RAG.
-
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gains across 15 benchmarks.
- MUR: Momentum Uncertainty guided Reasoning for Large Language Models