arXiv:2608. 12307v1 Announce Type: cross Abstract: Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods.
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods. In this paper, we ask whether such transfer can instead occur at test time.
arXiv:2608. 11829v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning.
arXiv:2608. 13721v1 Announce Type: cross Abstract: In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student's current distribution.
TTSR (Test-Time Self-Reflection) is a framework that enables large language models to adapt during inference by alternating between a Student role that solves test questions and a Teacher role that analyzes failures and generates targeted variant questions. The method incorporates a weakness memory and a strategy note to guide exploration, reducing reliance on noisy pseudo-labels and inefficient rollouts. Experiments on mathematical reasoning benchmarks demonstrate consistent test-time improvements, strong cross-backbone generalization, and transfer to general-domain reasoning tasks.
The paper investigates how test‑time computation can enhance language models and at what cost, introducing the SELF‑POT benchmark to evaluate this across competition mathematics, competitive programming, and agentic workflows. SELF‑POT separates candidate coverage from final accuracy, tracks correctness transitions under revision, and measures protocol completion alongside task success. Using a unified budget rule, the study compares direct inference, parallel sampling, and self‑revision across five low‑cost reasoning models, revealing that selection rules and failure handling significantly influence gains and cost savings.
The paper investigates data efficiency and selection in On‑Policy Distillation (OPD) for large language models. It shows that 1‑shot OPD—training on a single example—consistently improves performance, especially when the example is hard, and that longer chain‑of‑thought (CoT) paths drive the gains rather than token entropy. Based on these findings, the authors propose a simple hard‑example selection strategy that, using only eight carefully chosen hard examples, matches the performance of a 17,000‑example baseline across models from 1.5B to 7B parameters.
The paper introduces Drift-Constrained Optimization (DCO), a framework that treats behavioral drift during fine‑tuning of instruction models as a bounded constraint rather than an uncontrolled side effect. By defining a drift budget, the authors reformulate fine‑tuning as a direction‑selection problem, showing that choosing different update directions can qualitatively change outcomes. Experiments on Qwen3 models demonstrate that carefully selected directions improve scientific reasoning and multilingual translation while preserving reasoning capabilities and general performance.
arXiv:2606. 31048v1 Announce Type: cross Abstract: This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.
arXiv:2603. 26556v2 Announce Type: replace-cross Abstract: Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs.
arXiv:2607.22629v3 Announce Type: replace Abstract: Large Reasoning Models produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate t...
arXiv:2609.22566v1 Announce Type: cross Abstract: Knowledge distillation (KD) aims to compress high-performance teacher LLMs into lightweight students. However, distilled students often exhibit subst...
Draft-OPD introduces an on‑policy distillation method for speculative draft models, addressing the mismatch between supervised fine‑tuning and inference by letting the target model supervise the drafter on draft‑induced states. The approach uses target‑assisted rollouts for stable continuations and replays drafting from error positions exposed during verification, enabling the drafter to learn from both accepted and rejected proposals. Experiments demonstrate that Draft‑OPD achieves more than five‑fold lossless acceleration across diverse tasks, outperforming prior draft models such as EAGLE‑3 and DFlash by 23 % and 13 % respectively.