🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

Cool paper on Skill routing for LLM agents. Real tasks rarely map to a single skill. They need several composed together, but most skill routing still treats the problem as picking one tool from a library. This work formalizes Compositional Skill Routing, decomposes a complex query into atomic sub-tasks, retrieves the right skill for each, and then composes an executable plan. The system, SkillWeaver, pairs an LLM decomposer with a bi-encoder FAISS retriever and a dependency-aware DAG planner. It comes with CompSkillBench, 300 compositional queries over 2,209 real skills, so the multi-skill case gets measured directly. Why does it matter? As skill libraries grow, single-skill retrieval quietly caps what an agent can do. The DAG planner turns retrieved skills into an ordered, dependency-respecting plan. Paper: https://t.co/OvyScHiis1 Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

Media 1

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2067618845926510770/media_0.jpg",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-06-18T14:48:53.523086",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2067618845926510770",
  "url": "https://x.com/omarsar0/status/2067618845926510770",
  "twitterUrl": "https://twitter.com/omarsar0/status/2067618845926510770",
  "text": "Cool paper on Skill routing for LLM agents.\n\nReal tasks rarely map to a single skill. They need several composed together, but most skill routing still treats the problem as picking one tool from a library.\n\nThis work formalizes Compositional Skill Routing, decomposes a complex query into atomic sub-tasks, retrieves the right skill for each, and then composes an executable plan.\n\nThe system, SkillWeaver, pairs an LLM decomposer with a bi-encoder FAISS retriever and a dependency-aware DAG planner.\n\nIt comes with CompSkillBench, 300 compositional queries over 2,209 real skills, so the multi-skill case gets measured directly.\n\nWhy does it matter?\n\nAs skill libraries grow, single-skill retrieval quietly caps what an agent can do. The DAG planner turns retrieved skills into an ordered, dependency-respecting plan.\n\nPaper: https://t.co/OvyScHiis1\n\nLearn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX",
  "source": "Twitter for iPhone",
  "retweetCount": 1,
  "replyCount": 2,
  "likeCount": 5,
  "quoteCount": 0,
  "viewCount": 324,
  "createdAt": "Thu Jun 18 14:42:02 +0000 2026",
  "lang": "en",
  "bookmarkCount": 6,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2067618845926510770",
  "displayTextRange": [
    0,
    278
  ],
  "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": 307744,
    "following": 868,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 36781,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4720,
    "statusesCount": 18316,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2067268161611739213"
    ],
    "profile_bio": {
      "description": "Building self-improving AI @dair_ai • Prev: Meta AI | PhD • Learn about AI Agents for FREE here: https://t.co/P5SA9u54xO",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "academy.dair.ai/courses/elemen…",
              "expanded_url": "https://academy.dair.ai/courses/elements-of-ai-agents",
              "indices": [
                97,
                120
              ],
              "url": "https://t.co/P5SA9u54xO"
            }
          ],
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                27,
                35
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypkSM"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/4BZHjkTil9",
        "expanded_url": "https://twitter.com/omarsar0/status/2067618845926510770/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": [
              {
                "h": 89,
                "w": 89,
                "x": 755,
                "y": 1201
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 89,
                "w": 89,
                "x": 755,
                "y": 1201
              }
            ]
          }
        },
        "id_str": "2067618841937788928",
        "indices": [
          279,
          302
        ],
        "media_key": "3_2067618841937788928",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARyxqGHMm0AACgACHLGoYrpaULIAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLGoYcybQAAKAAIcsahiulpQsgAA",
            "media_key": "3_2067618841937788928"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLGoYcybQAAVLHR.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": 1910,
              "w": 955,
              "x": 239,
              "y": 0
            },
            {
              "h": 1910,
              "w": 1470,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1910,
          "width": 1470
        },
        "sizes": {
          "large": {
            "h": 1910,
            "w": 1470
          }
        },
        "type": "photo",
        "url": "https://t.co/4BZHjkTil9"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2606.18051",
        "expanded_url": "https://arxiv.org/abs/2606.18051",
        "indices": [
          828,
          851
        ],
        "url": "https://t.co/OvyScHiis1"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          904,
          927
        ],
        "url": "https://t.co/1e8RZKs4uX"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}