hahnli

Qwen3-8B-Search-MaximinRL-W2S

hahnli/Qwen3-8B-Search-MaximinRL-W2S

Qwen3-8B-Search-MaximinRL-W2S is a machine learning model from hahnli. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

This is a research checkpoint trained on the SearchR1 environment using RL with a game-theoretic maximin objective between a stronger agent (Qwen3-8B) and a weaker monitor (Qwen2.5-3B-Instruct), which forms a weak-to-…