Skip to content
aiqbench takeAI Research

aiqbench analysis

This research introduces RepoReuse, a novel benchmark that exposes critical inefficiencies in coding agents by measuring code redundancy rather than just functional pass rates. The study reveals that as agents iterate, they increasingly fail to leverage existing repository history, duplicating logic in over half of task chains while maintaining high accuracy scores. This finding underscores the urgent need for evaluation metrics that account for structural duplication and auditability in automated software development workflows.
Sources coveringarXiv, Fortune
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Do Coding Agents Reuse Existing Code or Reinvent the Wheel?

arXiv2 min read

arXiv:2609.35357v1 Announce Type: cross Abstract: Coding agents are increasingly deployed for iterative development on real repositories, yet existing evaluation barely answers a basic question: \emph{do coding agents reuse existing code or reinvent the wheel?} The question matters: every duplicated implementation is a fix applied twice and agents produce code far faster than humans can audit, so redundancy accumulates unsupervised. Thus, we present \textbf{RepoReuse}, a multi-turn benchmark for auditing code reuse in real repositories, where requirements are revealed turn by turn and the workspace accumulates across turns. It is built by a fully automated pipeline combining AST-based dependency graphs, guided evidence collection, and execution-verified task synthesis, and scales readily to new repositories. Beyond pass rates, we measure the reuse rate together with recall and cross-turn structural redundancy. An audit over 3{,}000 turns shows that agents progressively stop exploring relevant repository code, reuse their own history less even when it is fully in the workspace, and leave duplicated logic in 50.8\% of task chains by turn~5---all while pass rates barely move. Such deficiencies are invisible to pass rates, underscoring the need to evaluate code generation beyond functional correctness.

Title:Do Coding Agents Reuse Existing Code or Reinvent the Wheel?

Abstract:Coding agents are increasingly deployed for iterative development on real repositories, yet existing evaluation barely answers a basic question: \emph{do coding agents reuse existing code or reinvent the wheel?} The question matters: every duplicated implementation is a fix applied twice and agents produce code far faster than humans can audit, so redundancy accumulates unsupervised. Thus, we present \textbf{RepoReuse}, a multi-turn benchmark for auditing code reuse in real repositories, where requirements are revealed turn by turn and the workspace accumulates across turns. It is built by a fully automated pipeline combining AST-based dependency graphs, guided evidence collection, and execution-verified task synthesis, and scales readily to new repositories. Beyond pass rates, we measure the reuse rate together with recall and cross-turn structural redundancy. An audit over 3{,}000 turns shows that agents progressively stop exploring relevant repository code, reuse their own history less even when it is fully in the workspace, and leave duplicated logic in 50.8\% of task chains by turn~5---all while pass rates barely move. Such deficiencies are invisible to pass rates, underscoring the need to evaluate code generation beyond functional correctness.

Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

arXiv:2609.35357 [cs.SE]

(or arXiv:2609.35357v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2609.35357 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Full text under the publisher's open licence · 292 words

Related coverage