🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

This is one of the most interesting papers on self-improving agents for this year. (bookmark this one) Most self-improving AI systems hit the same wall: the mechanism that generates improvements is fixed and can't improve itself. This new work from Meta and collaborators breaks through this limitation. They introduce Hyperagents, self-referential agents where the self-improvement process itself is editable. The DGM-Hyperagent combines a task agent and a meta agent into a single modifiable program, enabling metacognitive self-modification. It autonomously discovers innovations like persistent memory and performance tracking, and these meta-improvements transfer across domains and compound across runs. Why does it matter? - On paper review, DGM-H improved from 0.0 to 0.710 test accuracy. - On robotics reward design, it went from 0.060 to 0.372. - Transfer hyperagents achieved 0.630 on Olympiad-level math grading in a domain they were never trained on. This is a step toward AI systems that don't just find better solutions but continuously improve how they search for improvements. Paper: https://t.co/Q0f7zWhNMD Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

Media 1
Media 2

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2036828723878793335/media_0.jpg",
      "filename": "media_0.jpg"
    },
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2036828723878793335/media_1.png",
      "filename": "media_1.png"
    }
  ],
  "processed_at": "2026-03-25T15:36:26.256564",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2036828723878793335",
  "url": "https://x.com/omarsar0/status/2036828723878793335",
  "twitterUrl": "https://twitter.com/omarsar0/status/2036828723878793335",
  "text": "This is one of the most interesting papers on self-improving agents for this year.\n\n(bookmark this one)\n\nMost self-improving AI systems hit the same wall: the mechanism that generates improvements is fixed and can't improve itself.\n\nThis new work from Meta and collaborators breaks through this limitation.\n\nThey introduce Hyperagents, self-referential agents where the self-improvement process itself is editable.\n\nThe DGM-Hyperagent combines a task agent and a meta agent into a single modifiable program, enabling metacognitive self-modification.\n\nIt autonomously discovers innovations like persistent memory and performance tracking, and these meta-improvements transfer across domains and compound across runs.\n\nWhy does it matter?\n\n- On paper review, DGM-H improved from 0.0 to 0.710 test accuracy.\n\n- On robotics reward design, it went from 0.060 to 0.372.\n\n- Transfer hyperagents achieved 0.630 on Olympiad-level math grading in a domain they were never trained on.\n\nThis is a step toward AI systems that don't just find better solutions but continuously improve how they search for improvements.\n\nPaper: https://t.co/Q0f7zWhNMD\n\nLearn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX",
  "source": "Twitter for iPhone",
  "retweetCount": 1,
  "replyCount": 0,
  "likeCount": 2,
  "quoteCount": 0,
  "viewCount": 170,
  "createdAt": "Wed Mar 25 15:33:04 +0000 2026",
  "lang": "en",
  "bookmarkCount": 8,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2036828723878793335",
  "displayTextRange": [
    0,
    274
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 295249,
    "following": 795,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 35198,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4566,
    "statusesCount": 17527,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2036819915097940174"
    ],
    "profile_bio": {
      "description": "Building @dair_ai • Prev: Meta AI, Elastic, PhD • New AI learning portal: https://t.co/1e8RZKs4uX",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "academy.dair.ai",
              "expanded_url": "https://academy.dair.ai/",
              "indices": [
                74,
                97
              ],
              "url": "https://t.co/1e8RZKs4uX"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                9,
                17
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypSIk"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/ytHRIVRh0Y",
        "expanded_url": "https://twitter.com/omarsar0/status/2036828723878793335/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2036828719571202048",
        "indices": [
          275,
          298
        ],
        "media_key": "3_2036828719571202048",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxERO3KWvAACgACHERE7ssbkHcAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHERE7cpa8AAKAAIcRETuyxuQdwAA",
            "media_key": "3_2036828719571202048"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HERE7cpa8AAgxf5.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 862,
              "w": 1540,
              "x": 0,
              "y": 900
            },
            {
              "h": 1540,
              "w": 1540,
              "x": 0,
              "y": 222
            },
            {
              "h": 1756,
              "w": 1540,
              "x": 0,
              "y": 6
            },
            {
              "h": 1762,
              "w": 881,
              "x": 0,
              "y": 0
            },
            {
              "h": 1762,
              "w": 1540,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1762,
          "width": 1540
        },
        "sizes": {
          "large": {
            "h": 1762,
            "w": 1540
          }
        },
        "type": "photo",
        "url": "https://t.co/ytHRIVRh0Y"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2603.19461",
        "expanded_url": "https://arxiv.org/abs/2603.19461",
        "indices": [
          1113,
          1136
        ],
        "url": "https://t.co/Q0f7zWhNMD"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          1189,
          1212
        ],
        "url": "https://t.co/1e8RZKs4uX"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}