AOPD modifies on-policy distillation by using localized divergence minimization for non-positive advantages instead of negative reinforcement, yielding average gains of 4.09/8.34 over standard OPD on math reasoning benchmarks under strong/weak initialization.
Step-wise adaptive integration of supervised fine-tuning and reinforcement learning for task-specific llms
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Prefix-RFT blends SFT and RFT via prefix sampling from demonstrations to outperform standalone SFT, RFT, and mixed-policy baselines on math reasoning problems.
AnE combines Truth Anchor Expansion and Scaffold-Stripping to deliver 10.3% gains on eight multimodal reasoning benchmarks for MLLMs.
Correcting DeepSpeed optimizer and OpenRLHF loss bugs reveals SFT-then-RL outperforms mixed-policy methods by 3.8-22.2 points on math benchmarks.
EvoCoT uses self-generated and verified CoT trajectories in a two-stage curriculum to let LLMs learn from initially unsolved hard problems in RLVR settings.
RL-PLUS is a hybrid RL approach for LLMs that combines internal exploitation with external data via importance sampling and exploration advantages to prevent capability boundary collapse and achieve gains on math and OOD reasoning benchmarks.
Excessive SFT reduces LLM plasticity for RL; Rejuvenation restores it via base-anchored fusion and targeted neuron resets, yielding better RL performance and OOD generalization.
FEST improves RLVR sample efficiency on math and coding benchmarks by combining supervised signals, on-policy signals, and decaying weights on just 128 randomly chosen demonstrations, matching full-dataset baselines.
citing papers explorer
-
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
AOPD modifies on-policy distillation by using localized divergence minimization for non-positive advantages instead of negative reinforcement, yielding average gains of 4.09/8.34 over standard OPD on math reasoning benchmarks under strong/weak initialization.
-
Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
Prefix-RFT blends SFT and RFT via prefix sampling from demonstrations to outperform standalone SFT, RFT, and mixed-policy baselines on math reasoning problems.
-
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
AnE combines Truth Anchor Expansion and Scaffold-Stripping to deliver 10.3% gains on eight multimodal reasoning benchmarks for MLLMs.
-
SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
Correcting DeepSpeed optimizer and OpenRLHF loss bugs reveals SFT-then-RL outperforms mixed-policy methods by 3.8-22.2 points on math benchmarks.
-
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
EvoCoT uses self-generated and verified CoT trajectories in a two-stage curriculum to let LLMs learn from initially unsolved hard problems in RLVR settings.
-
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
RL-PLUS is a hybrid RL approach for LLMs that combines internal exploitation with external data via importance sampling and exploration advantages to prevent capability boundary collapse and achieve gains on math and OOD reasoning benchmarks.
-
When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff
Excessive SFT reduces LLM plasticity for RL; Rejuvenation restores it via base-anchored fusion and targeted neuron resets, yielding better RL performance and OOD generalization.
-
Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance
FEST improves RLVR sample efficiency on math and coding benchmarks by combining supervised signals, on-policy signals, and decaying weights on just 128 randomly chosen demonstrations, matching full-dataset baselines.