Stepwise-Querying is a method that extracts step-by-step explanations from a black-box teacher model without needing its internal chain-of-thought. By independently querying the teacher for intermediate derivations, validity checks, and corrections for each step, the gathered explanations are used to fine-tune smaller student models. Experiments on mathematics and code benchmarks show that this approach outperforms three baselines in 14 of 16 comparisons, and the introduced Stepwise Explanation Information Gain metric helps diagnose the usefulness of intermediate reasoning.
arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
arXiv:2607. 04572v1 Announce Type: new Abstract: Large language model (LLM) tutors often produce fluent step-by-step explanations, but a correct and pedagogically formatted response does not guarantee that the answer was derived from the student-facing problem.
arXiv:2609.37044v1 Announce Type: new Abstract: Explicit intermediate reasoning gives large language models (LLMs) a stronger problem-solving mode. We study learning from this think-mode advantage vi...
arXiv:2608.29623v1 Announce Type: cross Abstract: Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning...
CoTranslator is a method that converts reverse chain-of-thought (CoT) responses into verified forward CoT responses, enabling efficient large-scale generation and verification of training data for reasoning distillation. Trained on a small set of paired reverse and rejection-sampled forward responses, it improves student model accuracy on mathematics benchmarks by up to 5.82 percentage points and retains 95.0% of rejection sampling’s accuracy while using only 35.9% of its compute. The translator also transfers to new datasets, teachers, and STEM problems, boosting average STEM accuracy for 4B and 8B students by 4.88 and 4.31 percentage points, respectively.
arXiv:2610.02703v1 Announce Type: new Abstract: On-policy distillation (OPD) improves large language model reasoning by training students on their own rollouts with dense token-wise supervision from...
The paper introduces ReDiST, a framework that constructs student‑conditioned reasoning traces to enhance learning beyond answer‑only supervision. ReDiST revises student attempts using evidence and a verified answer, then selects the best traces with a frozen reader that evaluates answer recovery and probability. The distilled student is trained offline, and experiments on QA benchmarks show improved performance over baseline trace methods and highlight varying effectiveness across source and transfer settings.
arXiv:2609.38107v1 Announce Type: cross Abstract: Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning...
BoundaryEvo introduces a two‑stage data‑model co‑evolution framework for distilling long‑chain reasoning from large teacher models into small language models. First, Capability Priming distills a small set of teacher trajectories to give the student an initial reasoning baseline. Then, Capability‑Boundary Co‑Evolution iteratively selects questions the student has not mastered but the teacher can solve, updating the training data as the student’s capability grows. With only 1,000 examples, BoundaryEvo improves Qwen3.5‑4B accuracy from 62.9 % to 75.3 % on IMO‑AnswerBench and from 26.8 % to 46.0 % on AMO‑Bench, outperforming static and dynamic baselines across 11 benchmarks.
The paper introduces Validity-Calibrated Reasoning Distillation, a new framework for transferring multi-step reasoning from large language models to smaller ones. Unlike prior methods that rely on static teacher‑student hierarchies and trajectory imitation, this approach treats distillation as a local learning‑signal allocation problem. By comparing the teacher’s and student’s next‑step actions under the same prefix and modulating updates based on their relative local validity, the method provides dynamic, context‑dependent supervision that preserves structural guidance while adapting to local reasoning quality. Experiments on math, code, and instruction‑following benchmarks show that this strategy outperforms strong distillation baselines.
Ladders-of-Thought (LoT) is a framework that enhances reasoning in small- to mid-scale large language models by automatically generating easier variants of reasoning problems and organizing them into difficulty buckets. It uses a self‑evolving bandit scheduler to adaptively allocate training, improving performance across math and multi‑hop reasoning tasks on 1–8 B models. LoT achieves significant gains (e.g., +32 pp on AddSub, +16 pp on QASC) and converges faster than staged curricula.