Qwen-AgentWorld-35B-A3B

模型发布 Hugging Face 模型 · Qwen 原文语言:中文

官方机构模型仓库创建于 2026-06-22。仓库创建时间不等于正式发布日期。任务类型:text-generation

全文

Qwen-AgentWorld-35B-A3B

📑 Technical Report 📖 Blog 🤗 Hugging Face 🤖 ModelScope 💻 GitHub 🖥️ Demo

[!Note] This repository contains the model weights and configuration files for Qwen-AgentWorld-35B-A3B, a native language world model trained for agentic environment simulation.

These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.

Qwen-AgentWorld is the first language world model to cover seven agent interaction domains within a single model. It simulates agentic environments via long chain-of-thought reasoning, predicting the next environment state given an agent's action and interaction history. Trained through a three-stage pipeline — CPT injects environment knowledge, SFT activates next-state-prediction reasoning, RL sharpens simulation fidelity — Qwen-AgentWorld is a native world model: environment modeling is the training objective from the CPT stage onward, not a post-hoc add-on.

Highlights

Seven Unified Domains. A single model covers MCP (tool calling), Search, Terminal, SWE (software engineering), Android, Web, and OS — spanning both text and GUI interaction environments. Native World Model. Environment modeling from CPT onward, not post-hoc adaptation on a general-purpose LLM. Generalizable, Scalable & Controllable Simulator. Zero-shot generalization to OOD environments (e.g., OpenClaw); controllable perturbations and fictional-world construction surpass real-environment training. Agent Foundation Model. LWM RL warm-up on single-turn, non-agentic trajectories transfers to multi-turn, tool-calling agentic tasks across 7 benchmarks, including 3 entirely out-of-domain.

Model Overview

Type: Causal Language Model (Language World Model) Base Model: Qwen3.5-35B-A3B-Base Training Stage: Continual Pre-Training (CPT) → Supervised Fine-Tuning (SFT) → Reinforcement Learning (RL, GSPO) Number of Parameters: 35B in total and 3B activated Hidden Dimension: 2048 Token Embedding: 248320 (Padded) Number of Layers: 40 Hidden Layout: 10 × (3 × (Gated DeltaNet → MoE) → 1 × (Gated Attention → MoE)) Gated DeltaNet: - Number of Linear Attention Heads: 32 for V and 16 for QK - Head Dimension: 128 Gated Attention: - Number of Attention Heads: 16 for Q and 2 for KV - Head Dimension: 256 - Rotary Position Embedding Dimension: 64 Mixture Of Experts - Number of Experts: 256 - Number of Activated Experts: 8 Routed + 1 Shared - Expert Intermediate Dimension: 512 Context Length: 262,144 tokens Disclaimer: No outputs from external API services are included in the training pipeline.

Performance

AgentWorldBench (Open-Ended Evaluation)

Five-dimensional rubric mean per domain, normalized to 0-100 scale.

Model MCP Search Term. SWE Android Web OS Overall GPT-5.4 70.10 37.26 53.69 66.29 60.00 51.80 68.58 58.25 Claude Opus 4.8 54.93 35.14 59.18 64.10 61.50 54.66 66.62 56.59 Claude Opus 4.6 69.90 29.30 57.51 64.55 61.74 51.42 70.20 57.80 Gemini 3.1 Pro 59.07 30.21 52.47 59.07 61.40 52.83 66.92 54.57 Claude Sonnet 4.6 70.00 28.79 56.98 64.52 58.03 50.78 63.17 56.04 DeepSeek-V4-Pro 63.27 27.61 51.26 59.44 55.17 50.32 63.70 52.97 GLM-5.1 67.60 22.46 47.32 52.07 59.10 51.50 59.13 51.31 Kimi K2.6 65.23 27.48 52.54 58.77 58.93 50.20 60.80 53.42 MiniMax-M2.7 55.82 27.30 41.62 37.44 52.40 50.52 57.73 46.12 Qwen3.5-35B-A3B 57.87 25.98 46.13 47.58 53.18 47.10 56.27 47.73 Qwen3.5-397B-A17B 68.31 30.81 55.30 64.44 54.90 48.55 60.85 54.74 Qwen3.6-Plus 55.28 21.94 50.58 59.08 57.65 50.78 60.33 50.81 Qwen-AgentWorld-35B-A3B 64.79 36.69 53.96 65.63 58.17 49.55 65.92 56.39 Qwen-AgentWorld-397B-A17B 68.24 37.82 57.73 68.49 60.20 50.98 67.89 58.71

Quickstart

Deployment

Qwen-AgentWorld-35B-A3B can be served via APIs with popular inference frameworks. In the following, we show example commands to launch OpenAI-compatible API servers.

[!Important] The model has a default context length of 262,144 tokens. If you encounter out-of-memory (OOM) errors, consider reducing the context window. However, because Qwen-AgentWorld leverages extended context for multi-turn environment simulation, we advise maintaining a context length of at least 128K tokens.

SGLang

SGLang is a fast serving framework for large language models.

An OpenAI-compatible API will be available at http://localhost:8000/v1.

vLLM

vLLM is a high-throughput and memory-efficient inference engine for LLMs.

The --language-model-only flag is required because the model architecture includes visual component definitions but the checkpoint only contains language model weights. Without this flag, vLLM will attempt to initialize visual modules and fail.

An OpenAI-compatible API will be available at http://localhost:8000/v1.

Inference with Transformers

Using via the Chat Completions API

[!Note] We provide domain-specific world model system prompt templates in prompts/ of the GitHub repository for all 7 domains. These serve as general-purpose system prompts when using Qwen-AgentWorld as an environment simulator. Each domain folder contains a system_prompt.txt (world model system prompt) and a judge_system_prompt.txt (evaluation prompt).

Evaluate on AgentWorldBench

AgentWorldBench evaluates language world models by scoring each predicted environment observation on 5 dimensions: Format, Factuality, Consistency, Realism, and Quality.

Setup

Run Evaluation

The evaluation follows a three-step pipeline:

Best Practices

Sampling Parameters: We recommend temperature=0.6, top_p=0.95, top_k=20 for world model inference. The model uses thinking mode by default ( ... ) to reason about environment state transitions before producing the predicted observation.

Adequate Output Length: We recommend an output length of 32,768 tokens for most queries. For long, multi-step trajectories, you may increase the max output length to accommodate detailed environment observations.

Domain-Specific System Prompts: For optimal simulation fidelity, use the domain-specific system prompts provided in the prompts/ directory of the GitHub repository.

正文以来源语言显示。

参考来源

← 返回每日简报