{
  "type": "tweet",
  "id": "2069720365442719867",
  "url": "https://x.com/Alibaba_Qwen/status/2069720365442719867",
  "twitterUrl": "https://twitter.com/Alibaba_Qwen/status/2069720365442719867",
  "text": "📣📣 Meet  Qwen-AgentWorld — a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training objective from day one, not a post-hoc adaptation.\n\n🤔 LLMs are trained to be better agents — better at acting in environments. But nobody has trained them to model the environments themselves.\n\n🗺️ Our roadmap: investigate how language world modeling can push the boundaries of general agent capabilities, along two routes:\n\n1️⃣ Build a foundation model for environment simulation — outperforming Claude Opus 4.8 and GPT-5.4 on AgentWorldBench\n\n2️⃣ Investigate how world modeling enhances agent training:\n🔬 Controllable Sim RL (agentic RL with LWM as environments) surpasses training in real environments\n🧠 Learning to predict environments (LWM warm-up) makes agents stronger — remarkably, even without any agent-specific training, this predictive knowledge transfers to agentic tasks with zero fine-tuning\n\n📑 Paper: https://t.co/Jx2l5RKq71\n📖 Blog: https://t.co/7tVcKyhsx2\n💻 GitHub: https://t.co/B5Lvb1UZCn\n🤗 HuggingFace: https://t.co/Kw3QBL1TM5\n🧩 ModelScope: https://t.co/YBnGYgMWWI",
  "source": "Twitter for iPhone",
  "retweetCount": 783,
  "replyCount": 201,
  "likeCount": 4705,
  "quoteCount": 247,
  "viewCount": 1079077,
  "createdAt": "Wed Jun 24 09:52:43 +0000 2026",
  "lang": "en",
  "bookmarkCount": 3529,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2069720365442719867",
  "displayTextRange": [
    0,
    276
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "Alibaba_Qwen",
    "url": "https://x.com/Alibaba_Qwen",
    "twitterUrl": "https://twitter.com/Alibaba_Qwen",
    "id": "1753339277386342400",
    "name": "Qwen",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": "Business",
    "profilePicture": "https://pbs.twimg.com/profile_images/2064231947149377536/Ab70PxT5_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1753339277386342400/1780986224",
    "description": "",
    "location": "",
    "followers": 223710,
    "following": 6,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Fri Feb 02 08:47:32 +0000 2024",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 402,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 484,
    "statusesCount": 910,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2061506641120641494"
    ],
    "profile_bio": {
      "description": "Open foundation models for AGI.",
      "entities": {
        "description": {},
        "url": {
          "urls": [
            {
              "display_url": "qwen.ai",
              "expanded_url": "https://qwen.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/f8hrbNCQR4"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/ahvxH66uxT",
        "expanded_url": "https://twitter.com/Alibaba_Qwen/status/2069720365442719867/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2069720354491117568",
        "indices": [
          277,
          300
        ],
        "media_key": "3_2069720354491117568",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy5H7JR1rAACgACHLkftN6a4HsAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLkfslHWsAAKAAIcuR+03prgewAA",
            "media_key": "3_2069720354491117568"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLkfslHWsAAxwe3.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 672,
              "w": 1200,
              "x": 0,
              "y": 0
            },
            {
              "h": 703,
              "w": 703,
              "x": 0,
              "y": 0
            },
            {
              "h": 703,
              "w": 617,
              "x": 0,
              "y": 0
            },
            {
              "h": 703,
              "w": 352,
              "x": 0,
              "y": 0
            },
            {
              "h": 703,
              "w": 1200,
              "x": 0,
              "y": 0
            }
          ],
          "height": 703,
          "width": 1200
        },
        "sizes": {
          "large": {
            "h": 703,
            "w": 1200
          }
        },
        "type": "photo",
        "url": "https://t.co/ahvxH66uxT"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2606.24597",
        "expanded_url": "https://arxiv.org/abs/2606.24597",
        "indices": [
          1016,
          1039
        ],
        "url": "https://t.co/Jx2l5RKq71"
      },
      {
        "display_url": "qwen.ai/blog?id=qwen-a…",
        "expanded_url": "https://qwen.ai/blog?id=qwen-agentworld",
        "indices": [
          1048,
          1071
        ],
        "url": "https://t.co/7tVcKyhsx2"
      },
      {
        "display_url": "github.com/QwenLM/Qwen-Ag…",
        "expanded_url": "https://github.com/QwenLM/Qwen-AgentWorld",
        "indices": [
          1082,
          1105
        ],
        "url": "https://t.co/B5Lvb1UZCn"
      },
      {
        "display_url": "huggingface.co/collections/Qw…",
        "expanded_url": "https://huggingface.co/collections/Qwen/qwen-agentworld",
        "indices": [
          1121,
          1144
        ],
        "url": "https://t.co/Kw3QBL1TM5"
      },
      {
        "display_url": "modelscope.cn/collections/Qw…",
        "expanded_url": "https://modelscope.cn/collections/Qwen/Qwen-AgentWorld",
        "indices": [
          1159,
          1182
        ],
        "url": "https://t.co/YBnGYgMWWI"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}