29 results for "OpenAI Codex"
Showing 1–20 · 0.55 seconds · RSS
-
Preprint Full text
Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance
…This paper presents an empirical study comparing five popular agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, and Claude Code), analyzing 7,156 pull requests (PRs) from the AIDev dataset. Temporal trend analysis reveals heterogeneous evolution patterns: Devin exhibits the only consistent…
-
Preprint Full text
Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex
…evaluation and diagnosis. This report presents ATBench-Claw and ATBench-Codex, two domain-customized extensions that carry ATBench into the OpenClaw and OpenAI Codex / Codex-runtime settings. The key adaptation mechanism is to analyze each new setting, customize the three-dimensional Safety…
-
Preprint Full text
Sanity Checks for Agentic Data Science
Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers to statistical questions. However, these systems can reach falsely optimistic conclusions that are difficult for users…
-
Journal Article Full text
Agentic design of compositional descriptors via autoresearch for materials science applications
…tests chemically motivated descriptor strategies. We apply automat, using OpenAI Codex with GPT-5.5 as the coding agent, to predict experimental band gaps in inorganic materials and Curie temperatures in ferromagnetic compounds. Five independent runs are performed for each task. When used as inputs…
-
Book Full text
Mathematical Computing and Reproducible Experiments - English Edition
…retain their stated licenses. Production and translation assistance: OpenAI Codex gpt-5.6-sol, Ultra, at the user's direction. No endorsement by comparator authors is implied.
-
Preprint Full text
Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data
…The analysis and all note writing is carried out entirely by AI agents (OpenAI Codex and Anthropic Claude) under expert physicist direction. A fully corrected spectrum is obtained via Iterative Bayesian Unfolding and Monte Carlo based corrections. This work represents a step toward a…
-
Preprint Full text
Fingerprinting AI Coding Agents on GitHub
…AI coding agents, analyzing 33,580 PRs from five major agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, Claude Code) to identify behavioral signatures. With 41 features spanning commit messages, PR structure, and code characteristics, we achieve 97.2% F1-score in multi-class agent…
-
Preprint Full text
AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents
…We evaluate three state-of-the-art LLM coding agents (Claude Code, OpenAI Codex, and Gemini) across 300 projects generated from 100 standardized prompts in Python, JavaScript, and Java. We introduce a three-layer dependency framework (distinguishing between claimed, working, and runtime…
-
Preprint Full text
AIDev: Studying AI Coding Agents on GitHub
…AIDev aggregates 932,791 Agentic-PRs produced by five agents: OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code. These PRs span 116,211 repositories and involve 72,189 developers. In addition, AIDev includes a curated subset of 33,596 Agentic-PRs from 2,807 repositories with over 100…
-
Preprint Full text
How do Agents Refactor: An Empirical Study
Software development agents such as Claude Code, GitHub Copilot, Cursor Agent, Devin, and OpenAI Codex are being increasingly integrated into developer workflows. While prior work has evaluated agent capabilities for code completion and task automation, there is little work investigating how these…
-
Preprint Full text
SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring
…compound refactorings remain the primary source of failures; notably, an OpenAI Codex agent achieves only 39.4% success on compound instances. We release SWE-Refactor and all evaluation results to facilitate future research on LLM-based code refactoring.
-
Preprint Full text
ABTest: Behavior-Driven Testing for AI Coding Agents
…We apply ABTest to three widely used coding agents: Claude Code, OpenAI Codex CLI, and Gemini CLI. From 400 user-reported developer-confirmed agent failures, we extract 47 Interaction Patterns and 128 Action types, generating 647 repository-grounded fuzzing cases. Executing the 647-case bundle once…
-
Book Full text
Methods of Algebra, Volume 2: Linear Algebra - Independent English Edition
…configuration, metadata, and the modular backend were produced with OpenAI Codex gpt-5.6-sol, Ultra , acting on instructions of the user. This disclosure does not displace the source author or other human and component credits. This independent edition is not endorsed by Wen-Wei Li or Higher…
-
Preprint Full text
Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study
Autonomous coding agents (e.g., OpenAI Codex, Devin, GitHub Copilot) are increasingly used to generate fix-related pull requests (PRs) in real world software repositories. However, their practical effectiveness depends on whether these contributions are accepted and merged by project maintainers…
-
Preprint Full text
AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
…AgentPack, a corpus of 1.8M code edits co-authored by Claude Code, OpenAI Codex, and Cursor Agent across public GitHub projects up to early October 2025. We describe the identification and curation pipeline, quantify adoption trends of these agents, and analyze the structural properties of the…
-
Preprint Full text
Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
…of lines of source code. We compare five popular coding agents, including OpenAI Codex, Claude Code, GitHub Copilot, Google Jules, and Devin, examining how their usage differs in various development aspects such as merge frequency, edited file types, and developer interaction signals, including…
-
Book Full text
Methods of Algebra, Volume 1: Basic Structures — Independent English Edition
…preserve these distinctions. Translation and editorial production: OpenAI Codex gpt-5.6-sol, Ultra, on instructions of the user. Source authorship and human credits are retained. This independent edition claims no official affiliation, approval, or endorsement.
-
Book Full text
Luc Illusie — The Cotangent Complex and Deformations, Volumes I and II: English translation
…translation, editorial corrections, and typesetting were produced by OpenAI Codex — GPT-5.6 Sol, Ultra effort . No human editor prepared or reviewed these editions. Each PDF is immediately followed by its directly downloadable cumulative LaTeX source and the complete source archive needed to…
-
Preprint Full text
Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering
…granularity of a line or function, modern agentic systems -- Claude Code, OpenAI Codex CLI, Google Jules, Devin, OpenHands, SWE-agent, MetaGPT, ChatDev, and DeepMind's AlphaEvolve -- operate at the granularity of a repository, a feature, or an algorithm. We synthesize work from Anthropic, OpenAI…
-
Preprint Full text
Greedy Is a Strong Default: Agents as Iterative Optimizers
…simulated annealing, parallel investigators, and even a second LLM model (OpenAI Codex) provide no benefit over greedy hill climbing while requiring 2-3x more evaluations. In our setting, the LLM's learned prior appears strong enough that acceptance-rule sophistication has limited impact--round 1…