{
  "schema_version": "1",
  "generated_at": "2026-10-20T00:00:00Z",
  "$schema": "https://agentpaywire.com/schemas/library.schema.json",
  "license": "links + original short summaries; content belongs to publishers",
  "category": "datasets-benchmarks",
  "count": 6,
  "categories": [
    {
      "id": "bitcoin-lightning",
      "label": "Bitcoin and Lightning",
      "featured": true,
      "count": 24,
      "json_url": "https://agentpaywire.com/api/library/bitcoin-lightning.json",
      "markdown_url": "https://agentpaywire.com/library/bitcoin-lightning.md",
      "html_url": "https://agentpaywire.com/library/bitcoin-lightning/"
    },
    {
      "id": "payments",
      "label": "Payments",
      "featured": false,
      "count": 48,
      "json_url": "https://agentpaywire.com/api/library/payments.json",
      "markdown_url": "https://agentpaywire.com/library/payments.md",
      "html_url": "https://agentpaywire.com/library/payments/"
    },
    {
      "id": "agent-protocols",
      "label": "Agent protocols",
      "featured": false,
      "count": 23,
      "json_url": "https://agentpaywire.com/api/library/agent-protocols.json",
      "markdown_url": "https://agentpaywire.com/library/agent-protocols.md",
      "html_url": "https://agentpaywire.com/library/agent-protocols/"
    },
    {
      "id": "robotics-autonomy",
      "label": "Robotics and autonomy",
      "featured": false,
      "count": 3,
      "json_url": "https://agentpaywire.com/api/library/robotics-autonomy.json",
      "markdown_url": "https://agentpaywire.com/library/robotics-autonomy.md",
      "html_url": "https://agentpaywire.com/library/robotics-autonomy/"
    },
    {
      "id": "iot",
      "label": "IoT",
      "featured": false,
      "count": 4,
      "json_url": "https://agentpaywire.com/api/library/iot.json",
      "markdown_url": "https://agentpaywire.com/library/iot.md",
      "html_url": "https://agentpaywire.com/library/iot/"
    },
    {
      "id": "datasets-benchmarks",
      "label": "Datasets and benchmarks",
      "featured": false,
      "count": 6,
      "json_url": "https://agentpaywire.com/api/library/datasets-benchmarks.json",
      "markdown_url": "https://agentpaywire.com/library/datasets-benchmarks.md",
      "html_url": "https://agentpaywire.com/library/datasets-benchmarks/"
    },
    {
      "id": "safety-security",
      "label": "Safety and security",
      "featured": false,
      "count": 4,
      "json_url": "https://agentpaywire.com/api/library/safety-security.json",
      "markdown_url": "https://agentpaywire.com/library/safety-security.md",
      "html_url": "https://agentpaywire.com/library/safety-security/"
    },
    {
      "id": "regulation",
      "label": "Regulation",
      "featured": false,
      "count": 1,
      "json_url": "https://agentpaywire.com/api/library/regulation.json",
      "markdown_url": "https://agentpaywire.com/library/regulation.md",
      "html_url": "https://agentpaywire.com/library/regulation/"
    }
  ],
  "entries": [
    {
      "id": "tau-bench",
      "title": "τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains",
      "publisher": "arXiv",
      "authors": [
        "Shunyu Yao",
        "Noah Shinn",
        "Pedram Razavi",
        "Karthik Narasimhan"
      ],
      "date_published": "2024-06-17",
      "url": "https://arxiv.org/abs/2406.12045",
      "type": "research-paper",
      "category": "datasets-benchmarks",
      "summary": "Benchmark of dynamic conversations between a language-model-simulated user and an agent equipped with domain-specific API tools and policy guidelines. Success is scored by comparing the final database state with an annotated goal state, and the paper introduces the pass^k reliability metric.",
      "tags": [
        "benchmark",
        "tools",
        "research"
      ],
      "verified_at": "2026-10-20",
      "last_checked": "2026-10-20",
      "http_status": 200,
      "archive_url": "http://web.archive.org/web/20261015183045/https://arxiv.org/abs/2406.12045"
    },
    {
      "id": "gaia-benchmark",
      "title": "GAIA: a benchmark for General AI Assistants",
      "publisher": "arXiv",
      "authors": [
        "Grégoire Mialon",
        "Clémentine Fourrier",
        "Craig Swift",
        "Thomas Wolf",
        "Yann LeCun",
        "Thomas Scialom"
      ],
      "date_published": "2023-11-21",
      "url": "https://arxiv.org/abs/2311.12983",
      "type": "research-paper",
      "category": "datasets-benchmarks",
      "summary": "Benchmark of real-world questions for general AI assistants that require reasoning, multimodality, web browsing and tool use.",
      "tags": [
        "benchmark",
        "research"
      ],
      "verified_at": "2026-10-20",
      "last_checked": "2026-10-20",
      "http_status": 200,
      "archive_url": "http://web.archive.org/web/20261011183417/https://arxiv.org/abs/2311.12983"
    },
    {
      "id": "swe-bench-paper",
      "title": "SWE-bench: Can Language Models Resolve Real-World GitHub Issues?",
      "publisher": "arXiv",
      "authors": [
        "Carlos E. Jimenez",
        "John Yang",
        "Alexander Wettig",
        "Shunyu Yao",
        "Kexin Pei",
        "Ofir Press",
        "Karthik Narasimhan"
      ],
      "date_published": "2023-10-10",
      "url": "https://arxiv.org/abs/2310.06770",
      "type": "research-paper",
      "category": "datasets-benchmarks",
      "summary": "Evaluation framework of 2,294 software engineering problems drawn from real GitHub issues and pull requests across 12 popular Python repositories.",
      "tags": [
        "benchmark",
        "research"
      ],
      "verified_at": "2026-10-20",
      "last_checked": "2026-10-20",
      "http_status": 200,
      "archive_url": "http://web.archive.org/web/20261011232036/https://arxiv.org/abs/2310.06770"
    },
    {
      "id": "webarena",
      "title": "WebArena: A Realistic Web Environment for Building Autonomous Agents",
      "publisher": "arXiv",
      "authors": [
        "Shuyan Zhou",
        "Frank F. Xu",
        "Hao Zhu",
        "Xuhui Zhou",
        "Robert Lo",
        "Abishek Sridhar",
        "Xianyi Cheng",
        "Tianyue Ou",
        "Yonatan Bisk",
        "Daniel Fried",
        "Uri Alon",
        "Graham Neubig"
      ],
      "date_published": "2023-07-25",
      "url": "https://arxiv.org/abs/2307.13854",
      "type": "research-paper",
      "category": "datasets-benchmarks",
      "summary": "Highly realistic and reproducible web environment for building and testing language-guided agents that perform tasks on the web. The authors list shows the first 12 of a longer list.",
      "tags": [
        "benchmark",
        "web-agents",
        "research"
      ],
      "verified_at": "2026-10-20",
      "last_checked": "2026-10-20",
      "http_status": 200,
      "archive_url": "http://web.archive.org/web/20261002191854/https://arxiv.org/abs/2307.13854"
    },
    {
      "id": "swe-bench-leaderboards",
      "title": "SWE-bench Leaderboards",
      "publisher": "SWE-bench",
      "authors": [],
      "date_published": null,
      "url": "https://www.swebench.com/",
      "type": "docs",
      "category": "datasets-benchmarks",
      "summary": "Official SWE-bench site with leaderboards for SWE-bench, Verified, Multilingual, Multimodal and Lite variants, plus related tools.",
      "tags": [
        "benchmark",
        "leaderboard"
      ],
      "verified_at": "2026-10-20",
      "last_checked": "2026-10-20",
      "http_status": 200,
      "archive_url": "http://web.archive.org/web/20261019081426/https://www.swebench.com/"
    },
    {
      "id": "open-x-embodiment",
      "title": "Open X-Embodiment: Robotic Learning Datasets and RT-X Models",
      "publisher": "Open X-Embodiment Collaboration",
      "authors": [],
      "date_published": null,
      "url": "https://robotics-transformer-x.github.io/",
      "type": "docs",
      "category": "datasets-benchmarks",
      "summary": "Project page of the Open X-Embodiment Collaboration presenting robotic learning datasets and RT-X models. It asks whether the consolidation around large pretrained models seen in NLP and computer vision can happen in robotics.",
      "tags": [
        "dataset",
        "robotics"
      ],
      "verified_at": "2026-10-20",
      "last_checked": "2026-10-20",
      "http_status": 200,
      "archive_url": "http://web.archive.org/web/20260905225407/https://robotics-transformer-x.github.io/"
    }
  ]
}