Skip to content
AI Atlas

A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning

Published 17 Sept 2026arXiv:2609.17804

data quality89

Updated 24 h ago · first seen 17 Sept 2026

paper_01M2Q5C6R2C7ZRF8Y8CDJ0SWTY

Abstract

Large language models solve grade-school math word problems with high accuracy, yet a single irrelevant clause inserted into the problem can collapse it. We reconcile these observations with a mechanistic account. We show that the model's internal computation decomposes into a four-stage sequential pipeline, Schema Abstraction, Operation Planning, Operand Binding, and Computation, each stage producing a distinct intermediate representation in an identifiable band of layers. Using the same scaffold to diagnose distractor-induced failure, we localize the corruption to a single stage, Operation Planning, implemented by a set of attention heads whose causal role we validate bidirectionally. In short, we provide a mechanistic interpretation of math word problem reasoning in LLMs, and their failure when distracted.

Authors

Authors 2

Carla P. GomesZhongdi Qu

Linked names open researcher pages (created from the paper's author list; name-only, no affiliation unless a source states it). Unlinked names have no researcher record yet.

Organizations

Organizations 0

No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.

Models

Models introduced or described 0

Inbound described_by relations from model cards and documentation.

No model links this paper yet

Model pages link papers through their model cards and documentation; the relation is written only when a source states it.

Datasets

Datasets used 0

No dataset relation recorded.

Benchmarks

Benchmarks used 0

No benchmark relation recorded.

Code

Repositories & frameworks 0

No repository linked.

Timeline

Timeline 2

Full timeline →

Sources

Sources 2

Source documents
SourceDocumentTypeTierLast observedSnapshots
arXiv (Atom API + RSS)rss.arxiv.org/rss/cs.AI feedT1· Official13 h ago7
arXiv (Atom API + RSS)rss.arxiv.org/rss/cs.LG feedT1· Official13 h ago6

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.