Metraipolis › archive › dc_5b256cf85632

OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review — arXiv:2608.09290

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09290
License (as archived)
CC0-1.0
Archived
2026-10-19T09:00:59.616Z
SHA-256 of the archived text
21a988ae5b374c1935b1bebd4c03167d36d0d1714430d95cc6c8cac9007ba556
Stable URL of this page
https://metraipolis.com/documento/dc_5b256cf85632

How to cite

OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review — arXiv:2608.09290 — arXiv (en), https://arxiv.org/abs/2608.09290 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5b256cf85632 (Metraipolis archive dc_5b256cf85632, sha256 21a988ae5b374c1935b1bebd4c03167d36d0d1714430d95cc6c8cac9007ba556)
BibTeX
@misc{dc5b256cf85632,
  title = {OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review — arXiv:2608.09290},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09290},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5b256cf85632; sha256 21a988ae5b374c1935b1bebd4c03167d36d0d1714430d95cc6c8cac9007ba556},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09290. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based code review agents promise scalable, always-on review, yet current systems suffer from two intertwined weaknesses: (1) non-determinism--unbounded tool use makes review outcomes unstable, and (2) context locality--the reviewer's access remains bounded to the diff, capping discoverable issue depth. Both give rise to three challenges: misaligned context retrieval, a coherence-efficiency trade-off in multi-file pull requests, and hallucinated comments that erode trust. To address these, we introduce OpenCodeReview, built on deterministic engineering for uncertain agents: rather than granting maximal freedom, we inject determinism at three deliberate pipeline points. Rule-Guided Dispatch uses a multi-layer rule system to deterministically select files and review criteria, eliminating variability of agent-driven triage. Grounded File Review replaces free-form exploration with a curated tool set exposed through a ReAct loop, while file-level parallel SubAgents balance context coherence against efficiency and recover cross-file dependencies on demand. Independent Reflection introduces a falsification-first filter under an asymmetric information boundary--the reflector sees only the diff, not the agent's tool-augmented exploration--removing hallucinated comments without self-reinforcing bias, improving precision while preserving recall. On AACR-Bench (200 real-world PRs, 10 languages, 1,505 expert-verified comments), OpenCodeReview outperforms mainstream coding agents (e.g., Claude Code and Codex) across six LLM backends, achieving up to 2.17x higher SEM-F1 (25.10% vs. 11.57%) while consuming 5-15x fewer tokens. We open-source OpenCodeReview at this https URL .

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.09290 — 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 2026-10-19T09:00:31.494Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).