Metraipolis › archive › dc_1febb071bf63
WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents — arXiv:2610.22039
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22039
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:02:20.265Z
- SHA-256 of the archived text
3e6fe53b1707fa16abe98da71606f595107b11e6116fc86b58d4c88a77725a7c- Stable URL of this page
https://metraipolis.com/documento/dc_1febb071bf63
How to cite
WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents — arXiv:2610.22039 — arXiv (en), https://arxiv.org/abs/2610.22039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1febb071bf63 (Metraipolis archive dc_1febb071bf63, sha256 3e6fe53b1707fa16abe98da71606f595107b11e6116fc86b58d4c88a77725a7c)
BibTeX
@misc{dc1febb071bf63,
title = {WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents — arXiv:2610.22039},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22039},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1febb071bf63; sha256 3e6fe53b1707fa16abe98da71606f595107b11e6116fc86b58d4c88a77725a7c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requiring coordinated modifications across a repository. Yet most executable repository-level benchmarks retain a single issue or PR as the task unit, while existing multi-PR settings rely on coarse aggregation and structure-agnostic evaluation. This mismatch obscures dependencies among changes and limits progress measurement and learning signals for long-horizon code agents. We introduce WEAVE, a framework that transforms verified PR histories into executable, dependency-structured tasks. WEAVE leverages repository-calibrated typed change loci to organize related PRs into bounded DAGs and instantiate each as a unified executable task. We further introduce Graph Credit, a deterministic, test-grounded metric that measures dependency-consistent partial progress and supports dense, verifiable rewards for reinforcement learning. Experiments on task construction, agent evaluation, supervised fine-tuning, and reinforcement learning show that WEAVE yields coherent executable tasks, enables more faithful progress measurement than flat scoring, and provides effective supervision and verifiable rewards for training code agents. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.22039 — 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 2026-10-16T08:44:47.768Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).