Zero2Repo: Can Coding Agents Build Repositories from Scratch?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
The Flow has not summarised this story yet — read it at arXiv AI.
E2E-SWE is a benchmark that tests large language models’ ability to create complete, functional software repositories from scratch. It includes 186 tasks across 11 programming languages, each requiring an agent to build an installable project based solely on a natural‑language specification and an empty workspace, while passing a hidden test suite. The benchmark was crafted by software engineers and LLMs, then refined through iterative verification by autonomous agents to ensure clarity and solvability.
ProgramGym introduces a scalable framework for training long-horizon program reproduction agents, comprising Program-Env and Program-Agent components. Program-Env builds verifiable training environments from repositories via a feedback loop that repairs sandbox builds and improves black-box tests, yielding 1,648 environments across C, C++, Go, and Rust. Program-Agent employs a role-isolated workflow of analysis, implementation, and review with revision management, boosting performance on ProgramBench and raising Qwen3.8-27B’s accuracy from 34.87% to 42.84% and surpassing flagship models with fine-tuning.
arXiv:2608. 09072v1 Announce Type: cross Abstract: Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs.
arXiv:2610.09079v1 Announce Type: cross Abstract: Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete r...
The paper introduces Req2Test-Bench, a benchmark of 5,086 instances linking natural‑language Gherkin requirements to developer‑written test implementations across five languages and four BDD frameworks. It evaluates eight agent–model–reasoning setups, finding that while the best configuration (Codex with DeepSeek‑V4.1‑Flash) produces passing tests for 82.8% of cases, only 33.8% are behaviorally adequate, as measured by kill‑completeness. The study highlights diminishing returns from scaling agents, the impact of under‑specified requirements, and the potential of requirement‑grounded harnesses to improve test generation.
FeatureArc is a new benchmark that evaluates coding agents on the evolution of software features, requiring agents to extend a feature across multiple stages while preserving earlier functionality. The benchmark uses a pipeline that constructs tasks from real repository histories, validates fail‑to‑pass and pass‑to‑pass tests, and covers four programming languages. In tests on 73 tasks, agents performed well on the first stage (62.7% success) but dropped to 28.5% when the entire feature was evaluated, with inherited defects causing most failures.