Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study
cs.SE, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/openai/codex-plugin-cc
Sources
- Rethinking Code Review Workflows with LLM Assistance: An Empirical Study
- AutoMix: Automatically Mixing Language Models
- From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
- Humans or LLMs as the Judge? A Study on Judgement Biases
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning
- Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents
- Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- When to Screen, When to Bypass: LLM-Judges in Resource-Scarce AI-Human Workflow
- RouteLLM: Learning to Route LLMs with Preference Data
- LLM Evaluators Recognize and Favor Their Own Generations
- Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection
- Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
- When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
- When Does a Second Model Help? Cross-Model Review in LLM Verification
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- Agentless: Demystifying LLM-based Software Engineering Agents
- Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties