BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

• URL: http://arxiv.org/abs/2603.03194v1
• Date: Tue, 03 Mar 2026 17:52:01 GMT
• Title: BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
• Authors: Guoxin Chen, Fanzhe Meng, Jiale Zhao, Minghao Li, Daixuan Cheng, Huatong Song, Jie Chen, Yuzhi Lin, Hui Chen, Xin Zhao, Ruihua Song, Chang Liu, Cheng Chen, Kai Jia, Ji-Rong Wen,
• Abstract summary: We introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope.<n>To investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities.<n>This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.
• Score: 61.247730037229815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current benchmarks for code agents primarily assess narrow, repository-specific fixes, overlooking critical real-world challenges such as cross-repository reasoning, domain-specialized problem solving, dependency-driven migration, and full-repository generation. To address this gap, we introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope - using 500 real-world instances across four distinct settings. Experimental results reveal a significant capability gap: even frontier models plateau below 45% success, and no single model performs consistently across task types. To systematically investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities. Our experiments show that search augmentation yields inconsistent gains and can in some cases degrade performance, highlighting the difficulty of emulating developer-like workflows that interleave search and reasoning during coding tasks. This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.

Related papers

• Benchmarking Agents in Insurance Underwriting Environments [0.9728664856449597]
  Existing benchmarks overemphasize open-domains such as code, use narrow accuracy metrics, and lack authentic complexity.<n>We present UNDERWRITE, an expert-first, multi-turn insurance underwriting benchmark designed in close collaboration with domain experts.
  arXiv  Detail & Related papers  (2026-01-31T02:12:11Z)
• InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research [36.46396692622759]
  We introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research.<n>It comprises 20 tasks spanning Data Construction, Filtering, Augmentation, Loss Design, Reward Design, and Scaffold Construction.<n>We also develop ResearchGym, a research environment offering rich action spaces, distributed and long-horizon execution, asynchronous monitoring, and snapshot saving.
  arXiv  Detail & Related papers  (2025-10-31T16:22:23Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios [63.67884284105684]
  We introduce textbfUltraHorizon, a novel benchmark that measures the foundational capabilities essential for complex real-world challenges.<n>Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules.<n>Our experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores.
  arXiv  Detail & Related papers  (2025-09-26T02:04:00Z)
• DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learning [5.280613615397194]
  DynaSearcher is an innovative search agent enhanced by dynamic knowledge graphs and multi-reward reinforcement learning (RL)<n>We employ a multi-reward RL framework for fine-grained control over training objectives such as retrieval accuracy, efficiency, and response quality.<n> Experimental results demonstrate that our approach achieves state-of-the-art answer accuracy on six multi-hop question answering datasets.
  arXiv  Detail & Related papers  (2025-07-23T09:58:31Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing [84.16442052968615]
  We introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE)<n>RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning.<n>We conduct experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models.
  arXiv  Detail & Related papers  (2025-04-03T17:59:56Z)
• 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)
• A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond [84.95530356322621]
  This survey presents a systematic review of the advancements in code intelligence.<n>It covers over 50 representative models and their variants, more than 20 categories of tasks, and an extensive coverage of over 680 related works.<n>Building on our examination of the developmental trajectories, we further investigate the emerging synergies between code intelligence and broader machine intelligence.
  arXiv  Detail & Related papers  (2024-03-21T08:54:56Z)

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.