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

• URL: http://arxiv.org/abs/2608.09290v2
• Date: Tue, 11 Aug 2026 03:48:22 GMT
• Title: OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review
• Abstract summary: We introduce OpenCodeReview, built on deterministic engineering for uncertain agents.<n>On AACR-Bench (200 real-world PRs, 10 languages, 1,505 expert-verified comments), OpenCodeReview outperforms mainstream coding agents.
• Score: 14.707064801983172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 https://github.com/alibaba/open-code-review.

Related papers

• Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories [0.0]
  Persistent context files (AGENTS.md, CLAUDE.md) are standard practice for guiding AI coding agents, yet evidence for their effectiveness is contradictory.<n>We present a controlled ablation of context-injection strategy across two frontier agents (Claude Code and Codex)
  arXiv  Detail & Related papers  (2026-07-28T11:07:53Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review [47.72392142544407]
  Coding agents increasingly generate pull requests (PRs) for real-world software issues.<n>One-shot PR generation remains open-loop: the PR is proposed without systematic review, diagnosis, or revision.<n>We introduce textbfSWE-Review, a framework for closing this loop with agentic code review.
  arXiv  Detail & Related papers  (2026-07-07T09:37:45Z)
• PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception [75.70273182182397]
  PerceptionRubrics is a rubric-based evaluation framework.<n>It addresses the gap between saturated benchmark scores and real-world brittleness.<n>It pairs 1,038 information-dense images with over 10,000 instance-specific rubrics.
  arXiv  Detail & Related papers  (2026-06-26T17:59:15Z)
• What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs [52.50210189669399]
  Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs)<n>We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation.<n>We show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods.
  arXiv  Detail & Related papers  (2026-06-01T03:18:01Z)
• MuMuTestUp: Mutation-based Multi-Agent Test Case Update [8.951495370176216]
  We propose MuMuTestUp, a mutation-guided multi-agent framework with three specialized agents.<n>MuMuTestUp generates repair instructions for uncovered lines/branches, handles hallucinations via semantic-similarity search.<n>We also construct PRBENCH, a 571-sample pull-request-level dataset from 10 open-source Java projects.
  arXiv  Detail & Related papers  (2026-05-19T02:25:25Z)
• Affordance Agent Harness: Verification-Gated Skill Orchestration [45.231685718099264]
  Affordance grounding requires identifying where and how an agent should interact in open-world scenes.<n>We propose Affordance Agent Harness, a closed-loop runtime that unifies skills with an evidence store and cost control.
  arXiv  Detail & Related papers  (2026-05-01T13:45:16Z)
• RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow [0.5607590231264274]
  This paper demonstrates how agentic AI principles can revolutionize software maintenance tasks by presenting RAG-Reflect.<n>RAG-Reflect is a modular framework that achieves fine-tuned-level performance for valid comment-edit prediction without task-specific training.<n>We evaluate RAG-Reflect on the publicly available SOUP benchmark, achieving Precision = 0.81, Recall = 0.74, and F1 = 0.78.
  arXiv  Detail & Related papers  (2026-04-24T04:49:58Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery [0.685316573653194]
  Refute-or-Promote is an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)<n>We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)<n>We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)
  arXiv  Detail & Related papers  (2026-04-21T03:55:35Z)
• Reviewing the Reviewer: Elevating Peer Review Quality through LLM-Guided Feedback [75.31379834079648]
  We introduce an LLM-driven framework that decomposes reviews into argumentative segments.<n>We also release LazyReviewPlus, a dataset of 1,309 sentences labeled for lazy thinking and specificity.
  arXiv  Detail & Related papers  (2026-01-17T20:32:18Z)
• Towards Practical Defect-Focused Automated Code Review [8.370750734081088]
  We explore the full automation pipeline within the online recommendation service, analyzing industry-grade C++s.<n>We identify four key challenges: 1) capturing relevant context, 2) improving key inclusion, 3) reducing false alarm rates (FAR), and 4) integrating human bug slicing.<n>Our approach, validated on real-world merge requests from historical fault reports, achieves a 2x improvement over standard LLMs and a 10x gain over previous baselines.
  arXiv  Detail & Related papers  (2025-05-23T14:06:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.