RLRT augments GRPO by reinforcing tokens on correct student rollouts that the teacher would not have predicted, outperforming standard self-distillation and exploration baselines on Qwen3 models.
Expanding the capabilities of reinforcement learning via text feedback
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
GUI-SD introduces on-policy self-distillation with visually enriched privileged context and entropy-guided weighting, outperforming GRPO and naive OPSD on six GUI grounding benchmarks while improving training efficiency.
Prefix Sampling replays self-generated trajectory prefixes to control rollout pass rates to ~50% in binary-reward GRPO, delivering 2.01x and 1.55x speedups on Qwen3-14B/32B with slight score improvements on SWE-bench Verified.
FlexSQL reaches 65.4% on Spider2-Snow by allowing agents to flexibly explore schemas, generate diverse plans, choose SQL or Python execution, and apply two-tiered repair.
CoARS enables co-evolving recommender and user agents by using interaction-derived rewards and self-distilled credit assignment to internalize multi-turn feedback into model parameters, outperforming prior agentic baselines.
SelfEvo enables pretrained 4D perception models to self-improve on unlabeled videos via self-distillation, delivering up to 36.5% relative gains in video depth estimation and 20.1% in camera estimation across eight benchmarks.
SPEAR enables online federated LLM fine-tuning by using feedback-guided self-play to create contrastive pairs trained with maximum likelihood on correct completions and confidence-weighted unlikelihood on incorrect ones, outperforming baselines without ground-truth contexts.
citing papers explorer
-
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
RLRT augments GRPO by reinforcing tokens on correct student rollouts that the teacher would not have predicted, outperforming standard self-distillation and exploration baselines on Qwen3 models.
-
Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding
GUI-SD introduces on-policy self-distillation with visually enriched privileged context and entropy-guided weighting, outperforming GRPO and naive OPSD on six GUI grounding benchmarks while improving training efficiency.
-
Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
Prefix Sampling replays self-generated trajectory prefixes to control rollout pass rates to ~50% in binary-reward GRPO, delivering 2.01x and 1.55x speedups on Qwen3-14B/32B with slight score improvements on SWE-bench Verified.
-
FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
FlexSQL reaches 65.4% on Spider2-Snow by allowing agents to flexibly explore schemas, generate diverse plans, choose SQL or Python execution, and apply two-tiered repair.
-
Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems
CoARS enables co-evolving recommender and user agents by using interaction-derived rewards and self-distilled credit assignment to internalize multi-turn feedback into model parameters, outperforming prior agentic baselines.
-
Self-Improving 4D Perception via Self-Distillation
SelfEvo enables pretrained 4D perception models to self-improve on unlabeled videos via self-distillation, delivering up to 36.5% relative gains in video depth estimation and 20.1% in camera estimation across eight benchmarks.
-
Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback
SPEAR enables online federated LLM fine-tuning by using feedback-guided self-play to create contrastive pairs trained with maximum likelihood on correct completions and confidence-weighted unlikelihood on incorrect ones, outperforming baselines without ground-truth contexts.