{
  "schema_version": 2,
  "title": "Reproduction: SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?",
  "emoji": "🎯",
  "space_id": "Yashp2003/repro-swe-fficiency-can-language-models-optimize-real-world-repositories-on-real-workloads",
  "paper": {
    "arxiv_id": "2511.06090"
  },
  "tags": [
    "icml2026-repro",
    "paper-0pyFbZSfbT"
  ],
  "updated_at": "2026-07-22T15:04:32+00:00",
  "root": {
    "slug": "index",
    "title": "Reproduction: SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?",
    "file": "pages/index.md",
    "children": [
      {
        "slug": "executive-summary",
        "title": "Executive summary",
        "file": "pages/executive-summary/page.md",
        "children": []
      },
      {
        "slug": "claim-1-the-swe-fficiency-benchmark-comprises-498-real-world-code-optimization-tasks-drawn-from-9-widely-used-python-repositories-including-numpy-pandas-and-scipy-abstract-only",
        "title": "Claim 1: The SWE-fficiency benchmark comprises 498 real-world code optimization tasks drawn from 9 widely used Python repositories including numpy, pandas, and scipy (abstract only).",
        "file": "pages/claim-1-the-swe-fficiency-benchmark-comprises-498-real-world-code-optimization-tasks-drawn-from-9-widely-used-python-repositories-including-numpy-pandas-and-scipy-abstract-only/page.md",
        "children": []
      },
      {
        "slug": "claim-2-agents-are-tasked-with-investigating-code-semantics-localizing-bottlenecks-and-relevant-tests-and-producing-a-patch-that-matches-or-exceeds-expert-speedup-while-passing-the-same-unit-tests-abstract-only",
        "title": "Claim 2: Agents are tasked with investigating code semantics, localizing bottlenecks and relevant tests, and producing a patch that matches or exceeds expert speedup while passing the same unit tests (abstract only).",
        "file": "pages/claim-2-agents-are-tasked-with-investigating-code-semantics-localizing-bottlenecks-and-relevant-tests-and-producing-a-patch-that-matches-or-exceeds-expert-speedup-while-passing-the-same-unit-tests-abstract-only/page.md",
        "children": []
      },
      {
        "slug": "claim-3-the-top-performing-agents-evaluated-on-swe-fficiency-achieve-less-than-0-23x-of-the-expert-level-speedup-on-average-across-the-498-tasks-abstract-only",
        "title": "Claim 3: The top-performing agents evaluated on SWE-fficiency achieve less than 0.23x of the expert-level speedup on average across the 498 tasks (abstract only).",
        "file": "pages/claim-3-the-top-performing-agents-evaluated-on-swe-fficiency-achieve-less-than-0-23x-of-the-expert-level-speedup-on-average-across-the-498-tasks-abstract-only/page.md",
        "children": []
      },
      {
        "slug": "claim-4-agents-struggle-specifically-with-localizing-optimization-opportunities-in-large-codebases-reasoning-about-execution-flow-across-multiple-functions-and-maintaining-correctness-of-proposed-optimizations-abstract-only",
        "title": "Claim 4: Agents struggle specifically with localizing optimization opportunities in large codebases, reasoning about execution flow across multiple functions, and maintaining correctness of proposed optimizations (abstract only).",
        "file": "pages/claim-4-agents-struggle-specifically-with-localizing-optimization-opportunities-in-large-codebases-reasoning-about-execution-flow-across-multiple-functions-and-maintaining-correctness-of-proposed-optimizations-abstract-only/page.md",
        "children": []
      },
      {
        "slug": "conclusion",
        "title": "Conclusion",
        "file": "pages/conclusion/page.md",
        "children": []
      }
    ]
  },
  "traces": [],
  "workspace": {
    "file": "workspace.json",
    "file_count": 0,
    "total_size": 0,
    "bucket_id": null
  },
  "agent_view_tokens": 3975,
  "trace_view_tokens": 10,
  "workspace_view_tokens": 8,
  "revision": "31eb59c0a761d4c0ade3"
}