← Back to all news
arXiv AI By Zhonghao Jiang, Xuyang Zheng, Yanfu Yan, Zhongxin Liu, Lingfeng Bao, Shuiguang Deng

Well-Specified and Well-Tested? Assessing SWE-bench-Style Datasets with a Self-Evolving Agent

Read the original on arXiv AI →

The paper introduces ExLabel, an LLM‑based, self‑evolving assistant that assesses task clarity and test coverage in SWE‑bench‑style software engineering datasets. ExLabel builds an experience bank from cross‑instance knowledge, enabling context‑aware judgments that outperform static rubrics. A new benchmark, SWE‑TQ, spanning eight programming languages, demonstrates ExLabel’s superior F1 scores and its ability to filter data that improves a coding model’s success rate on SWE‑bench Verified.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 12

SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories

SWE-Critix is a post‑training pipeline that creates generalist verifiers for coding‑agent trajectories. It uses supervised fine‑tuning followed by reinforcement learning to train 30B models on CodeForge‑Preview data, enabling the verifier to predict completion labels and generate natural‑language explanations. The approach raises classification accuracy from 57% to 78% on a held‑out test set.

By Jiajun Hu, Chun Yong Chong
llmsagentsreinforcement-learningfine-tuning
More like this →
arXiv AI
Oct 16

Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration

The paper introduces AXIOM, a perturbation-based framework for creating a balanced benchmark of code evaluation problems. AXIOM refines program quality by applying controlled semantic perturbations and then calibrates scores through selective manual annotation, resulting in the multilingual AXIOMBENCH dataset with 1,962 problems. This approach addresses limitations of prior benchmarks that rely on coarse binary labels or subjective human scoring.

By Ruiqi Wang, Xinchen Wang, Cuiyun Gao, Chun Yong Chong, Xin Xia, Qing Liao
llmsbenchmarkssafety
More like this →
arXiv AI
Jul 14

SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks

arXiv:2507. 11059v3 Announce Type: replace-cross Abstract: The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset.

By Pavel Adamenko, Mikhail Ivanov, Aidar Valeev, Rodion Levichev, Pavel Zadorozhny, Ivan Lopatin, Dmitry Babaev, Alena Fenogenova, Valentin Malykh
llmsagentsbenchmarks
More like this →
arXiv AI
Jun 3

Toward Training Superintelligent Software Agents through Self-Play SWE-RL

arXiv:2512. 18552v3 Announce Type: replace-cross Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.

By Yuxiang Wei, Zhiqing Sun, Emily McMilin, Jonas Gehring, David Zhang, Gabriel Synnaeve, Daniel Fried, Lingming Zhang, Sida Wang
llmsagentsreinforcement-learningbenchmarks
More like this →