SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents

• URL: http://arxiv.org/abs/2602.09447v2
• Date: Wed, 11 Feb 2026 07:41:43 GMT
• Title: SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents
• Authors: Zhirui Zhang, Hongbo Zhang, Haoxiang Fei, Zhiyuan Bao, Yubin Chen, Zhengyu Lei, Ziyue Liu, Yixuan Sun, Mingkun Xiao, Zihang Ye, Yu Zhang, Hongcheng Zhu, Yuxiang Wen, Heung-Yeung Shum,
• Abstract summary: SWE-AGI is an open-source benchmark for evaluating end-to-end, specification-driven construction of software systems written in MoonBit.<n>Each task involves implementing 1,000-10,000 lines of core logic, corresponding to weeks or months of engineering effort for an experienced human developer.
• Score: 21.8776989802963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although large language models (LLMs) have demonstrated impressive coding capabilities, their ability to autonomously build production-scale software from explicit specifications remains an open question. We introduce SWE-AGI, an open-source benchmark for evaluating end-to-end, specification-driven construction of software systems written in MoonBit. SWE-AGI tasks require LLM-based agents to implement parsers, interpreters, binary decoders, and SAT solvers strictly from authoritative standards and RFCs under a fixed API scaffold. Each task involves implementing 1,000-10,000 lines of core logic, corresponding to weeks or months of engineering effort for an experienced human developer. By leveraging the nascent MoonBit ecosystem, SWE-AGI minimizes data leakage, forcing agents to rely on long-horizon architectural reasoning rather than code retrieval. Across frontier models, gpt-5.3-codex achieves the best overall performance (solving 19/22 tasks, 86.4%), outperforming claude-opus-4.6 (15/22, 68.2%), and kimi-2.5 exhibits the strongest performance among open-source models. Performance degrades sharply with increasing task difficulty, particularly on hard, specification-intensive systems. Behavioral analysis further reveals that as codebases scale, code reading, rather than writing, becomes the dominant bottleneck in AI-assisted development. Overall, while specification-driven autonomous software engineering is increasingly viable, substantial challenges remain before it can reliably support production-scale development.

Related papers

• LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces [65.11019654023978]
  LongCLI-Bench is a benchmark designed to evaluate agentic capabilities across long-horizon, realistic tasks.<n>We curated 20 high-quality, long-horizon tasks from over 1,000 computer science assignments and real-world tasks.<n>Experiments reveal that even state-of-the-art agents achieve pass rates below 20% in LongCLI-Bench.
  arXiv  Detail & Related papers  (2026-02-15T23:12:57Z)
• ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development [72.4729759618632]
  We introduce ABC-Bench, a benchmark to evaluate agentic backend coding within a realistic, executable workflow.<n>We curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories.<n>Our evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks.
  arXiv  Detail & Related papers  (2026-01-16T08:23:52Z)
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• KAT-Coder Technical Report [48.00975798131211]
  KAT-Coder is a large-scale agentic code model trained through a multi-stage curriculum encompassing Mid-Term Training, Supervised Fine-Tuning (SFT), Reinforcement Fine-Tuning (RFT), and Reinforcement-to-Deployment Adaptation.<n>These stages enable KAT-Coder to achieve robust tool-use reliability, instruction alignment, and long-context reasoning.
  arXiv  Detail & Related papers  (2025-10-21T16:27:47Z)
• Dynamic Benchmark Construction for Evaluating Large Language Models on Real-World Codes [33.80591142965565]
  We present CODE2BENCH, a pipeline for dynamically constructing robust and contamination-resistant benchmarks from real-world GitHub repositories.<n>Specifically, CODE2BENCH introduces three key innovations: (1) Automated Dynamism, achieved through periodic ingestion of recent code to minimize training data contamination; (2) Scope Graph-based dependency analysis, which enables structured classification of functions into benchmark instances with controlled dependency levels; and (3) Property-Based Testing (PBT) for the automated synthesis of rigorous test suites.
  arXiv  Detail & Related papers  (2025-08-10T05:06:36Z)
• Evaluating Large Language Models on Non-Code Software Engineering Tasks [4.381476817430934]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code understanding and generation.<n>We present the first comprehensive benchmark, which we name Software Engineering Language Understanding' (SELU)<n>SELU covers classification, regression, Named Entity Recognition (NER) and Masked Language Modeling (MLM) targets, with data drawn from diverse sources.
  arXiv  Detail & Related papers  (2025-06-12T15:52:32Z)
• GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents [33.71705923246233]
  GSO is a benchmark for evaluating language models' capabilities in developing high-performance software.<n>SWE-Agents struggle significantly, achieving less than 5% success rate, with limited improvements even with inference-time scaling.<n>We release the code and artifacts of our benchmark along with agent trajectories to enable future research.
  arXiv  Detail & Related papers  (2025-05-29T17:14:55Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Human-In-the-Loop Software Development Agents [12.830816751625829]
  Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks.<n>In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development.<n>We design, implement, and deploy the HULA framework into Atlassian for internal uses.
  arXiv  Detail & Related papers  (2024-11-19T23:22:33Z)
• Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement [62.94719119451089]
  Lingma SWE-GPT series learns from and simulating real-world code submission activities. Lingma SWE-GPT 72B resolves 30.20% of GitHub issues, marking a significant improvement in automatic issue resolution.
  arXiv  Detail & Related papers  (2024-11-01T14:27:16Z)

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.