Fine-tuning a 7B model to match empirical next-event distributions from repeated concurrent Go executions yields 36.2% accuracy on 798 held-out production bug traces while improving calibration over standard cross-entropy training.
Qwen3.6-35B-A3B: Agentic coding power, now open to all, April 2026a
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
citing papers explorer
-
When the Next Step Is Not One Step: Distribution-Aware Execution Modeling for Concurrent Go Programs
Fine-tuning a 7B model to match empirical next-event distributions from repeated concurrent Go executions yields 36.2% accuracy on 798 held-out production bug traces while improving calibration over standard cross-entropy training.
-
Qwen-AgentWorld: Language World Models for General Agents
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.