{
  "id": 112444,
  "title": "SWE-Touch: Benchmarking Coding Agents When Users Touch the Code",
  "url": "https://urgent.news/2026/08/03/swe-touch-benchmarking-coding-agents-when-users-touch-the-code",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-03T17:03:19.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.02499v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task, yet existing repository-level benchmarks typically evaluate agents working alone or restrict user participation to messages. This leads us to ask: how do coding agents understand and respond to code changes in a shared workspace? We introduce…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}