🐦 Twitter Post Details

Viewing enriched Twitter post

@dair_ai

// Evolving Meta-Skill for Multi-Agent Systems // Can a multi-agent system get better at orchestration without touching a single weight? Automatic MAS generation has been stuck between two bad options. Inference-time methods use frozen frontier models but never learn from past runs. Training-time methods learn but are capped by small-model capability. Skill-MAS takes a third path. It treats the orchestration capability as an evolvable Meta-Skill, refined through a closed loop of multi-trajectory rollout and selective reflection that distills experience into strategy-level principles rather than memorized traces. Across four benchmarks and four different LLMs, the evolved Meta-Skills transfer to unseen tasks and other models, because the know-how lives in text at the strategy level, not in any one model's weights. You keep the frontier model and still accumulate experience. Paper: https://t.co/fn4J2Gz33M Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c

Media 1

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2068380866997588221/media_0.jpg",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-06-20T17:16:07.109692",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2068380866997588221",
  "url": "https://x.com/dair_ai/status/2068380866997588221",
  "twitterUrl": "https://twitter.com/dair_ai/status/2068380866997588221",
  "text": "// Evolving Meta-Skill for Multi-Agent Systems //\n\nCan a multi-agent system get better at orchestration without touching a single weight?\n\nAutomatic MAS generation has been stuck between two bad options. Inference-time methods use frozen frontier models but never learn from past runs. Training-time methods learn but are capped by small-model capability.\n\nSkill-MAS takes a third path.\n\nIt treats the orchestration capability as an evolvable Meta-Skill, refined through a closed loop of multi-trajectory rollout and selective reflection that distills experience into strategy-level principles rather than memorized traces.\n\nAcross four benchmarks and four different LLMs, the evolved Meta-Skills transfer to unseen tasks and other models, because the know-how lives in text at the strategy level, not in any one model's weights.\n\nYou keep the frontier model and still accumulate experience.\n\nPaper: https://t.co/fn4J2Gz33M\n\nLearn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c",
  "source": "Twitter for iPhone",
  "retweetCount": 0,
  "replyCount": 0,
  "likeCount": 3,
  "quoteCount": 0,
  "viewCount": 172,
  "createdAt": "Sat Jun 20 17:10:02 +0000 2026",
  "lang": "en",
  "bookmarkCount": 2,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2068380866997588221",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "dair_ai",
    "url": "https://x.com/dair_ai",
    "twitterUrl": "https://twitter.com/dair_ai",
    "id": "889050642903293953",
    "name": "DAIR.AI",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1643277398522187778/31dedbLo_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/889050642903293953/1773242460",
    "description": "",
    "location": "",
    "followers": 126359,
    "following": 1,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sun Jul 23 09:12:45 +0000 2017",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 4622,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 252,
    "statusesCount": 3340,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2067984002376749525"
    ],
    "profile_bio": {
      "description": "Democratizing AI research, education, and technologies. Learn about AI Agents for FREE at https://t.co/HHXg8rryu4",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "academy.dair.ai/courses/elemen…",
              "expanded_url": "https://academy.dair.ai/courses/elements-of-ai-agents",
              "indices": [
                90,
                113
              ],
              "url": "https://t.co/HHXg8rryu4"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/lkqPZtMU5s"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/2FdTeEDdR7",
        "expanded_url": "https://twitter.com/dair_ai/status/2068380866997588221/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": [
              {
                "h": 118,
                "w": 118,
                "x": 728,
                "y": 336
              },
              {
                "h": 204,
                "w": 204,
                "x": 100,
                "y": 1388
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 118,
                "w": 118,
                "x": 728,
                "y": 336
              },
              {
                "h": 204,
                "w": 204,
                "x": 100,
                "y": 1388
              }
            ]
          }
        },
        "id_str": "2068380863033958400",
        "indices": [
          280,
          303
        ],
        "media_key": "3_2068380863033958400",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy0XW+pWuAACgACHLRdcJWbEP0AAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLRdb6la4AAKAAIctF1wlZsQ/QAA",
            "media_key": "3_2068380863033958400"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLRdb6la4AA1iVW.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 823,
              "w": 1470,
              "x": 0,
              "y": 0
            },
            {
              "h": 1470,
              "w": 1470,
              "x": 0,
              "y": 0
            },
            {
              "h": 1676,
              "w": 1470,
              "x": 0,
              "y": 0
            },
            {
              "h": 1834,
              "w": 917,
              "x": 138,
              "y": 0
            },
            {
              "h": 1834,
              "w": 1470,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1834,
          "width": 1470
        },
        "sizes": {
          "large": {
            "h": 1834,
            "w": 1470
          }
        },
        "type": "photo",
        "url": "https://t.co/2FdTeEDdR7"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2606.18837",
        "expanded_url": "https://arxiv.org/abs/2606.18837",
        "indices": [
          900,
          923
        ],
        "url": "https://t.co/fn4J2Gz33M"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          976,
          999
        ],
        "url": "https://t.co/LRnpZN7L4c"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}