The paper introduces INSPIRE, an Internalize-Then-Improve framework designed to enhance example-driven mathematical reasoning in large language models. It combines Reference-Guided Student Internalization (RGSI) to generate high-quality preference pairs with a staged rubric preference training that separates method learning from correctness. Experiments across various model sizes show consistent gains, even outperforming larger open-source models, and maintain performance on out-of-distribution mathematical tasks.
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.
DIAG is a Diagnostic Iterative Alignment and Generation framework designed to improve data efficiency in aligning large language models for mathematical reasoning. It adaptively reshapes the practice distribution by first diagnosing valid preference-pair yield to calibrate exploration and exploitation, then generating targeted practice from the model’s failure traces. The approach is theoretically framed as a teacher‑mediated approximation to KL‑regularized reweighting, and experiments show that DIAG increases preference-pair yield and reasoning performance under the same training budget.
Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation. When problems arrive sequentially, accumulating reusable experience across them can further improve performance.
arXiv:2605. 19723v2 Announce Type: replace-cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial intelligence systems.
YFPO (Yoked Feature Preference Optimization) is a neuron‑guided preference optimization framework that augments standard preference learning with internal neuron‑level rewards. It uses AttnLRP to identify math‑associated internal features and derives an auxiliary reward from the activation margin between preferred and dispreferred responses. Experiments on GSM8K with a compact language model show that these neuron‑guided rewards influence optimization dynamics and yield measurable improvements, indicating that internal representations can serve as lightweight, interpretable signals for reasoning‑oriented post‑training.
arXiv:2607. 06974v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation.
arXiv:2609.24760v1 Announce Type: new Abstract: When facing complex problems, humans tend to try various ideas for different issues. Human thinking patterns exhibit remarkable flexibility in adapting...
The paper investigates whether the high costs of training chain-of-thought reasoning models can be reduced through algorithmic design. It introduces an autocurriculum approach that lets the model select which problems to focus on during training, showing that this method provably improves both supervised fine‑tuning and reinforcement learning. For supervised fine‑tuning, autocurriculum requires exponentially fewer reasoning demonstrations by targeting prompts where the model struggles, while for reinforcement learning it decouples computational cost from the quality of the reference model, making the burn‑in cost nearly independent of target accuracy.
arXiv:2610. 02191v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlying their solutions.
arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribut...
arXiv:2601. 18778v3 Announce Type: replace Abstract: RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal.
arXiv:2602. 02405v2 Announce Type: replace-cross Abstract: Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the problem.