🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

Long-horizon AI research agents are mostly a state-management problem. It is not enough for an agent to reason well in the next turn. ML research requires task setup, implementation, experiments, debugging, and evidence tracking over hours or days. This new paper introduces AiScientist, a system for autonomous long-horizon engineering for ML research. The key idea is to keep control thin and state thick. A top-level orchestrator manages stage-level progress, while specialized agents repeatedly ground themselves in durable workspace artifacts: analyses, plans, code, logs, and experimental evidence. That "File-as-Bus" design matters. AiScientist improves PaperBench by 10.54 points over the best matched baseline and reaches 81.82 Any Medal% on MLE-Bench Lite. Removing File-as-Bus drops PaperBench by 6.41 points and MLE-Bench Lite by 31.82 points. Why does it matter? Autonomous research agents need durable project memory, not just longer chats. Paper: https://t.co/A84c75oumP Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2044436099121209546/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2044436099121209546/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-04-15T15:31:20.541032",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2044436099121209546",
  "url": "https://x.com/omarsar0/status/2044436099121209546",
  "twitterUrl": "https://twitter.com/omarsar0/status/2044436099121209546",
  "text": "Long-horizon AI research agents are mostly a state-management problem.\n\nIt is not enough for an agent to reason well in the next turn. ML research requires task setup, implementation, experiments, debugging, and evidence tracking over hours or days.\n\nThis new paper introduces AiScientist, a system for autonomous long-horizon engineering for ML research.\n\nThe key idea is to keep control thin and state thick. A top-level orchestrator manages stage-level progress, while specialized agents repeatedly ground themselves in durable workspace artifacts: analyses, plans, code, logs, and experimental evidence.\n\nThat \"File-as-Bus\" design matters. AiScientist improves PaperBench by 10.54 points over the best matched baseline and reaches 81.82 Any Medal% on MLE-Bench Lite. Removing File-as-Bus drops PaperBench by 6.41 points and MLE-Bench Lite by 31.82 points.\n\nWhy does it matter?\n\nAutonomous research agents need durable project memory, not just longer chats.\n\nPaper: https://t.co/A84c75oumP\n\nLearn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX",
  "source": "Twitter for iPhone",
  "retweetCount": 3,
  "replyCount": 0,
  "likeCount": 10,
  "quoteCount": 0,
  "viewCount": 852,
  "createdAt": "Wed Apr 15 15:22:04 +0000 2026",
  "lang": "en",
  "bookmarkCount": 14,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2044436099121209546",
  "displayTextRange": [
    0,
    276
  ],
  "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": 298164,
    "following": 810,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 35409,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4596,
    "statusesCount": 17635,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2044436099121209546"
    ],
    "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/shBIzywg4M",
        "expanded_url": "https://twitter.com/omarsar0/status/2044436099121209546/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": [
              {
                "h": 219,
                "w": 219,
                "x": 94,
                "y": 112
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 219,
                "w": 219,
                "x": 94,
                "y": 112
              }
            ]
          }
        },
        "id_str": "2044436095824478209",
        "indices": [
          277,
          300
        ],
        "media_key": "3_2044436095824478209",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxfS8wZmsABCgACHF9LzN4a4MoAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHF9LzBmawAEKAAIcX0vM3hrgygAA",
            "media_key": "3_2044436095824478209"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HF9LzBmawAE7UJp.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 765,
              "w": 1366,
              "x": 0,
              "y": 0
            },
            {
              "h": 1366,
              "w": 1366,
              "x": 0,
              "y": 0
            },
            {
              "h": 1557,
              "w": 1366,
              "x": 0,
              "y": 0
            },
            {
              "h": 1798,
              "w": 899,
              "x": 0,
              "y": 0
            },
            {
              "h": 1798,
              "w": 1366,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1798,
          "width": 1366
        },
        "sizes": {
          "large": {
            "h": 1798,
            "w": 1366
          }
        },
        "type": "photo",
        "url": "https://t.co/shBIzywg4M"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2604.13018",
        "expanded_url": "https://arxiv.org/abs/2604.13018",
        "indices": [
          969,
          992
        ],
        "url": "https://t.co/A84c75oumP"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          1045,
          1068
        ],
        "url": "https://t.co/1e8RZKs4uX"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}