🐦 Twitter Post Details

Viewing enriched Twitter post

@AndrewYNg

Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better. I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was painfully slow. We wanted to see if an agentic workflow can help researchers iterate faster. When we trained the system on ICLR 2025 reviews and measured Spearman correlation (higher is better) on the test set: - Correlation between two human reviewers: 0.41 - Correlation between AI and a human reviewer: 0.42 This suggests agentic reviewing is approaching human-level performance. The agent grounds its feedback by searching arXiv, so it works best in fields like AI where research is freely published there. It’s an experimental tool, but I hope it helps you with your research. Check it out here: https://t.co/n7ctnDilJJ

Media 1

πŸ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1993001922773893273/media_0.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1993001922773893273/media_0.jpg?",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2025-11-27T20:39:16.594099",
  "pipeline_version": "2.0"
}

πŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "1993001922773893273",
  "url": "https://x.com/AndrewYNg/status/1993001922773893273",
  "twitterUrl": "https://twitter.com/AndrewYNg/status/1993001922773893273",
  "text": "Releasing a new \"Agentic Reviewer\" for research papers. I started coding this as a weekend project, and @jyx_su made it much better.\n\nI was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was painfully slow. We wanted to see if an agentic workflow can help researchers iterate faster.\n\nWhen we trained the system on ICLR 2025 reviews and measured Spearman correlation (higher is better) on the test set:\n- Correlation between two human reviewers: 0.41\n- Correlation between AI and a human reviewer: 0.42\n\nThis suggests agentic reviewing is approaching human-level performance.\n\nThe agent grounds its feedback by searching arXiv, so it works best in fields like AI where research is freely published there. It’s an experimental tool, but I hope it helps you with your research.\n\nCheck it out here: https://t.co/n7ctnDilJJ",
  "source": "Twitter for iPhone",
  "retweetCount": 1003,
  "replyCount": 219,
  "likeCount": 5726,
  "quoteCount": 112,
  "viewCount": 633124,
  "createdAt": "Mon Nov 24 17:01:01 +0000 2025",
  "lang": "en",
  "bookmarkCount": 4596,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "1993001922773893273",
  "displayTextRange": [
    0,
    280
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "AndrewYNg",
    "url": "https://x.com/AndrewYNg",
    "twitterUrl": "https://twitter.com/AndrewYNg",
    "id": "216939636",
    "name": "Andrew Ng",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/733174243714682880/oyG30NEH_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/216939636/1483126470",
    "description": "",
    "location": "Palo Alto, CA",
    "followers": 1295800,
    "following": 1047,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Thu Nov 18 03:39:11 +0000 2010",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1659,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 442,
    "statusesCount": 1955,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1975614372799283423"
    ],
    "profile_bio": {
      "description": "Co-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs",
      "entities": {
        "description": {
          "hashtags": [
            {
              "indices": [
                97,
                100
              ],
              "text": "ai"
            },
            {
              "indices": [
                101,
                117
              ],
              "text": "machinelearning"
            },
            {
              "indices": [
                119,
                132
              ],
              "text": "deeplearning"
            },
            {
              "indices": [
                133,
                139
              ],
              "text": "MOOCs"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "andrewng.org",
              "expanded_url": "http://www.andrewng.org",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XidcMETENd"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/23V905fSqs",
        "expanded_url": "https://twitter.com/AndrewYNg/status/1993001922773893273/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {},
          "orig": {}
        },
        "id_str": "1993001792142245888",
        "indices": [
          281,
          304
        ],
        "media_key": "3_1993001792142245888",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARuokJIRWwAACgACG6iQsHubwJkAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABG6iQkhFbAAAKAAIbqJCwe5vAmQAA",
            "media_key": "3_1993001792142245888"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/G6iQkhFbAAAcH2P.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 952,
              "w": 1700,
              "x": 0,
              "y": 0
            },
            {
              "h": 1210,
              "w": 1210,
              "x": 456,
              "y": 0
            },
            {
              "h": 1210,
              "w": 1061,
              "x": 531,
              "y": 0
            },
            {
              "h": 1210,
              "w": 605,
              "x": 759,
              "y": 0
            },
            {
              "h": 1210,
              "w": 1700,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1210,
          "width": 1700
        },
        "sizes": {
          "large": {
            "h": 1210,
            "w": 1700
          }
        },
        "type": "photo",
        "url": "https://t.co/23V905fSqs"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "urls": [
      {
        "display_url": "paperreview.ai",
        "expanded_url": "http://paperreview.ai",
        "indices": [
          885,
          908
        ],
        "url": "https://t.co/n7ctnDilJJ"
      }
    ],
    "user_mentions": [
      {
        "id_str": "1539636575474069505",
        "indices": [
          104,
          111
        ],
        "name": "Yixing Jiang",
        "screen_name": "jyx_su"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}