The paper presents a mechanistic analysis of how large language models solve grade‑school math word problems. It identifies a four‑stage sequential pipeline—Schema Abstraction, Operation Planning, Operand Binding, and Computation—each represented in distinct layer bands. The study shows that inserting an irrelevant clause disrupts the Operation Planning stage, pinpointing the cause of failure to specific attention heads.
arXiv:2604. 08571v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting.
arXiv:2607. 18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable.
The paper investigates how large language models perform propositional logical reasoning by conducting a causal mechanistic analysis on the PropLogic-MI benchmark. It identifies four interlocking mechanisms—Staged Computation, Information Transmission, Fact Retrospection, and Specialized Attention Heads—that organize the reasoning process across layers. The study demonstrates that these mechanisms recur across different model families, rule categories, and reasoning hops, indicating a structured, layer‑organized internal process for propositional reasoning.
arXiv:2510. 05969v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient resource allocation.
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.
The study investigates how lexical perturbations—such as keyboard noise, character swaps, and filler insertion—affect large language models (LLMs) on reasoning benchmarks. Four open-weight instruction-tuned models and frontier models were evaluated, revealing that character-level perturbations significantly reduce accuracy, especially on multi-step reasoning tasks, while filler insertion has minimal impact. The authors attribute this asymmetry to Attention Diversion, where fragmented subword tokenization draws disproportionate attention in middle and final transformer layers; they demonstrate that both token content and attention allocation are coupled, making it difficult for inference-time repair strategies to fully recover performance.
The paper investigates how large language models (LLMs) organize reasoning operations—such as problem formulation, goal decomposition, and deduction—within their hidden representation spaces. It shows that these operations are separable in held‑out representations, with peak separability in middle layers, and that token‑wise alignment of operations becomes more distributed across spans as layers deepen. Attention‑masking experiments reveal that representations aligned to operations at chunk onsets depend on prior reasoning context, indicating a geometric correspondence between linguistic reasoning expressions and internal model structure.
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:2607. 20520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures.
arXiv:2607. 08393v1 Announce Type: new Abstract: Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks.
arXiv:2601.06853v3 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting is widely adopted for mathematical problem solving, including in low-resource languages, yet its behavior un...
arXiv:2606. 16360v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead.