Qwen-AgentWorld: Language World Models for General Agents
Open paper
Benchmark
Model
Rank
Results
code-generation-on-swe-bench-verified
w/ LWM RL on Qwen3.5-35B-A3B-SFT (Internal agent scaffold (bash and file-edit tools))
#49
Accuracy: 67.86
Rank counts only results with a code link.