ATProto Browser

Record data

{
  "uri": "at://did:plc:rhkcyc46ubi523e47bhnkpbb/app.bsky.feed.post/3lozft2u3nl2k",
  "cid": "bafyreignc7nldjdkjvejurbv5v5yffuzqznfgtnaty7g4l3nj5h57jywz4",
  "value": {
    "text": "Absolute Zero: Reinforced Self-play Reasoning with Zero Data https://arxiv.org/abs/2505.03335v2 #AI #SelfPlayReasoning ",
    "$type": "app.bsky.feed.post",
    "embed": {
      "$type": "app.bsky.embed.images",
      "images": [
        {
          "alt": "Text Shot: To address these concerns, we propose a new RLVR paradigm called Absolute Zero, in which a single model learns to propose tasks that maximize its own learning progress and improves reasoning by solving them, without relying on any external data. Under this paradigm, we introduce the Absolute Zero Reasoner (AZR), a system that self-evolves its training curriculum and reasoning ability by using a code executor to both validate proposed code reasoning tasks and verify answers, serving as an unified source of verifiable reward to guide open-ended yet grounded learning. Despite being trained entirely without external data, AZR achieves overall SOTA performance on coding and mathematical reasoning tasks, outperforming existing zero-setting models that rely on tens of thousands of in-domain human-curated examples. Furthermore, we demonstrate that AZR can be effectively applied across different model scales and is compatible with various model classes.",
          "image": {
            "$type": "blob",
            "ref": {
              "$link": "bafkreicvwu5gso7k3sck2twlefejvskts4c3gw447xw7y6z3mwlewixd7m"
            },
            "mimeType": "image/png",
            "size": 309154
          }
        }
      ]
    },
    "facets": [
      {
        "index": {
          "byteEnd": 95,
          "byteStart": 61
        },
        "features": [
          {
            "uri": "https://arxiv.org/abs/2505.03335v2",
            "$type": "app.bsky.richtext.facet#link"
          }
        ]
      },
      {
        "index": {
          "byteEnd": 99,
          "byteStart": 96
        },
        "features": [
          {
            "tag": "AI",
            "$type": "app.bsky.richtext.facet#tag"
          }
        ]
      },
      {
        "index": {
          "byteEnd": 118,
          "byteStart": 100
        },
        "features": [
          {
            "tag": "SelfPlayReasoning",
            "$type": "app.bsky.richtext.facet#tag"
          }
        ]
      }
    ],
    "createdAt": "2025-05-13T02:11:07.618Z"
  }
}