Noisy expert imitation learning requires exponential samples for offline methods but polynomial for a variant of on-policy distillation under a noise condition.
hub Canonical reference
Self-Distilled RLVR
Canonical reference. 77% of citing Pith papers cite this work as background.
55
Pith papers citing it
Background
77% of classified citations
abstract
On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals for each sampled trajectory, in contrast to reinforcement learning with verifiable rewards (RLVR), which only obtains sparse signals from verifiable outcomes in the environment. Recently, the community has explored on-policy self-distillation (OPSD), where the same model serves as both teacher and student, with the teacher receiving additional privileged information such as reference answers to enable self-evolution. This paper demonstrates that learning signals solely derived from the privileged teacher result in severe information leakage and unstable long-term training. Accordingly, we identify the optimal niche for self-distillation and propose \textbf{RLSD} (\textbf{RL}VR with \textbf{S}elf-\textbf{D}istillation). Specifically, we leverage self-distillation to obtain token-level policy differences for determining fine-grained update magnitudes, while continuing to use RLVR to derive reliable update directions from environmental feedback (e.g., response correctness). This enables RLSD to simultaneously harness the strengths of both RLVR and OPSD, achieving a higher convergence ceiling and superior training stability.
hub tools
citation-role summary
background 10
baseline 2
method 1
citation-polarity summary
years
2026 55representative citing papers
CRAFT is a three-pillar credit assignment scheme that uses counterfactual token importance from GRPO sibling rollouts to provide signed per-token distillation signals in self-distilled agentic RL.
ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite with largest gains at the 0.8B scale.
A stop-gradient consistency regularizer mitigates context-induced degradation in on-policy distillation, improving robustness across 12 configurations.
OPRD performs distillation in hidden-state space on on-policy data for deterministic gradients and better math benchmark performance, plus OPRD-Bridge for cross-architecture transfer via low-rank projectors.
EST-PRM stress-tests five PRM models on 4,687 reasoning chains from MATH-500, GSM8K, and PRMBench using three label-preserving transformations and reports model-specific vulnerability patterns.
Temporal scheduling of credit allocation criteria over RLVR training, using trajectory percentiles to target heterogeneous behaviors, yields more stable policy entropy and better reasoning benchmark results than static allocation.
EDGE-OPD adds guided rollouts and evidence masking to on-policy self-distillation, enabling successful learning of target identities where standard OPSD and RLSD fail.
CEPO sharpens token credit in RLVR by requiring tokens to be favored by the correct answer and disfavored by wrong answers drawn from rejected rollouts, delivering accuracy gains on five multimodal math benchmarks.
VPD frames language feedback learning as variational EM so the teacher policy refines itself via trust-region updates on outcomes while the student learns dense token distributions on its own rollouts, outperforming fixed-teacher baselines on reasoning and code tasks.
EGRSD and CL-EGRSD advance the accuracy-length frontier in LLM reasoning by entropy-guided weighting of token-level distillation signals from the teacher.
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.
TRACE improves math reasoning by distilling only on annotator-marked critical spans with forward KL on correct key spans, optional reverse KL on errors, and GRPO elsewhere, gaining 2.76 points over GRPO while preserving OOD performance.
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
SRPO refines GRPO into role-aware token-level advantages by emphasizing perception tokens based on visual dependency (original vs. corrupted inputs) and reasoning tokens based on consistency with perception, unified via a shared baseline.
PBSD derives a reward-reweighted teacher distribution as the analytic optimum of a reward-regularized objective, yielding better stability and performance than KL-based self-distillation on math reasoning and tool-use tasks.
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
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.
NPO uses a policy's own near-future checkpoint as auxiliary trajectories to maximize effective learning signal S = Q/V, improving performance from 57.88 to 63.15 on Qwen3-VL-8B-Instruct with GRPO while accelerating convergence.
RLCSD contrasts teacher-student distributional gaps under correct versus wrong hints to suppress privilege-induced style drift and concentrate supervision on task tokens, outperforming GRPO and prior OPSD on Qwen3 and Olmo models.
ViCuR introduces recoverable visual cues as teacher privilege in multimodal on-policy distillation, yielding +1.19 to +1.24 average gains over answer-based baselines across seven benchmarks with Qwen3-VL students.
RLVR exhibits correct-set turnover where solved problems regress during training, and a periodic review mechanism exploiting a repair-window principle improves retention and performance over baselines.
ADWIN adaptively selects training horizons in on-policy distillation via prefix alignment checks, cutting end-to-end cost by up to 4.1x while matching or exceeding full-rollout accuracy on math and code benchmarks.
DASD improves math reasoning in LLMs by adaptively directing self-distillation based on per-token entropy to balance exploration and step accuracy, outperforming prior self-distillation and RLVR baselines on six benchmarks.
citing papers explorer
-
VISD: Enhancing Video Reasoning via Structured Self-Distillation
VISD proposes structured self-distillation with a multi-dimensional judge model and direction-magnitude decoupling to improve token-level credit assignment and convergence speed in VideoLLM reasoning training.