OEL + ReSAIL — Qwen3-4B — ALFWorld — Cycle 3

This repository contains the publicly released Cycle 3 checkpoint of OEL + ReSAIL, based on Qwen/Qwen3-4B and trained on ALFWorld.

ReSAIL augments iterative agent self-distillation with trajectory-balanced selective distillation and privileged retention.

Code and documentation: ShengjieJin/ReSAIL
All checkpoints: ReSAIL Collection

Evaluation

• Reported three-decoding-seed mean: ALFWorld ID 74.2%; ALFWorld OOD 67.2%.
• The reported variation is across decoding seeds, not independent training seeds.
• Thinking mode was disabled for the text-agent experiments.

Lineage

• Base model: Qwen/Qwen3-4B
• Training task: ALFWorld
• Method: OEL + ReSAIL
• Deployment cycle: 3

For environment setup, task data, training, and evaluation instructions, see the ReSAIL repository. The paper link and citation will be added when available.