Results indicate that math-capable LLMs organize internal mathematical computation by reasoning approach rather than benchmark topic, and the implication is that topic-stratified benchmarks and topic-balanced training corpora can still miss the axis that matters.
Abstract
Mathematical reasoning benchmarks are typically organized by topic, but language models may organize their internal computation by reusable reasoning approach instead. In this paper, we investigate whether open math-capable LLMs organize internally by topical sub-skill or by reasoning approach, and we present evidence that the approach is the key. We introduce a generation-replay protocol: a model first generates a solution, after which we replay the exact prompt-plus-generation trajectory and extract activation-importance signatures over the reasoning tokens. We cluster these signatures without supervision across eight models and five mathematical reasoning sources, then evaluate the recovered structure with structural, semantic, and intervention tests. Across all 40 model-source cells, the recovered clusters outperform matched-size random baselines. Two independent frontier-LLM judges find approach-level coherence in 77-82% of real clusters versus 6-11% in within-source controls, and topic-pure clusters usually receive labels finer than the topic itself. In approach-controlled prompting, changing the requested reasoning approach shifts cluster assignment in seven of eight model conditions, whereas paraphrases largely preserve it. These results indicate that math-capable LLMs organize internal mathematical computation by reasoning approach rather than benchmark topic. The implication is that topic-stratified benchmarks and topic-balanced training corpora can still miss the axis that matters: even deliberately topic-balanced corpora may remain imbalanced over reasoning approaches.
When selecting mathematical training data for LLMs, a natural organizing principle is topic: probability examples for probability targets. An alternative is reasoning approach: worked solutions that share a solution method with the target, even when the mathematical domain differs. We ask which relation produces greate...
Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-specific regularities. We study this distinction in small language models on the ARC-TGI benchmark, which organizes abstract grid transformations into controllable task famili...
Nur A. Zarin Nishat, Jens Lehmann, Andrei C. Aioanei et al.· 0 citations
Language models can now prove theorems, but people still decide which problems to pursue. We ask whether a model's internal representations can help identify promising mathematical connections. We develop LANTERN, a fast, cost-efficient pipeline that uses a classifier over pretrained-model activations to rank candidate...
P. Tikhonov, Elena Tutubalina, I. Oseledets et al.· arXiv.org· 0 citations
These stages establish a constructive post-training path from English-pivoted capability to multilingual reasoning that is reliably delivered, and jointly track correctness, language adherence, termination, and delivery efficiency.
Hong-Yang Li, Xiao Li, Caesar Wu et al.· arXiv.org· 0 citations
It is found that full trajectories provide only limited benefit, while partial trajectories are effective even under heavy truncation, and training LLMs using endpoints leads to consistent changes in reasoning behavior, and that it also benefits post-training methods based on reinforcement learning or on-policy distill...
Jaehui Hwang, Sangdoo Yun, Byeongho Heo et al.· 0 citations
Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive, or erroneous reasoning trajectories. In this work, we introduce a new interpretability framework, SLIDER, to evaluate the quality of the reasoning process. SLIDER leverag...