Metraipolis › archive › dc_ac5be93b4e8b
Code Understanding is a Bottleneck for Coding Agents — arXiv:2610.10610
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10610
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:53:33.842Z
- SHA-256 of the archived text
f29453ae543b68afaac1a356cca4dbdf7944ae6e1beab2afbaade4e0dfe094e4- Stable URL of this page
https://metraipolis.com/documento/dc_ac5be93b4e8b
How to cite
Code Understanding is a Bottleneck for Coding Agents — arXiv:2610.10610 — arXiv (en), https://arxiv.org/abs/2610.10610 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac5be93b4e8b (Metraipolis archive dc_ac5be93b4e8b, sha256 f29453ae543b68afaac1a356cca4dbdf7944ae6e1beab2afbaade4e0dfe094e4)
BibTeX
@misc{dcac5be93b4e8b,
title = {Code Understanding is a Bottleneck for Coding Agents — arXiv:2610.10610},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10610},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac5be93b4e8b; sha256 f29453ae543b68afaac1a356cca4dbdf7944ae6e1beab2afbaade4e0dfe094e4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10610. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Repository benchmarks (e.g., SWE-bench) for coding agents often assume that lines of code edited can predict task difficulty, but such datasets' poor control over code and task types makes it hard to know which abilities truly drive agent errors. We present CABRA: a Coding Ability Blueprint for Rigorous Agent evaluation. CABRA builds tasks from scratch as call graph transformations and scales difficulty via a task size parameter on four axes: function traversal, search, runtime resolution, and instruction following. We run eight LLMs and six coding agents on 6,840 CABRA tasks to show: 1) LLM accuracy falls as task size~grows, but agents stay near-perfect by offloading work to tools (e.g., grep); 2) Larger CABRA tasks elicit more tool calls for reading and analysis, while a separate study on SWE-bench Verified shows these tool call counts predict agents' accuracy better than lines of code edited, suggesting task difficulty for agents can lie in understanding code to edit, not just in making edits; 3) Extending CABRA to an intense understanding task where models analyze divergent logic across two classes backs this finding, as agent accuracy finally falls. More broadly, we argue for synthetic evaluations like CABRA to unmask LLM weaknesses trivialized by tools (e.g., needle-in-a-haystack) and abilities beyond just editing (e.g., understanding) that coding agents still find difficult, pairing SWE-bench-style tasks with controlled diagnosis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Programming Languages (cs.PL). Pagina del lavoro: https://arxiv.org/abs/2610.10610 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:47:01.206Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).