This is the final SkillForge policy for Search-Augmented QA: a full fine-tune of Qwen2.5-7B-Instruct trained with GRPO while its skill library was simultaneously forged — retired, stabilized, demoted and mutated — under the fitness-driven lifecycle described in the paper. Most memory-augmented agents keep the library append-only. A skill that was correct at step 20 encodes a procedure the policy has outgrown by step 120, and it is still being retrieved into the context. SkillForge instead scores each skill against the policy's own rollouts and moves it between four states — trial, active, stable, retired — so the library and the model co-evolve. On Search-Augmented QA this reaches 48.7%…
Open weights
mit
7.6B parameters
32,768 tokens
transformers
This is the final SkillForge policy for WebShop: a full fine-tune of Qwen2.5-7B-Instruct trained with GRPO while its skill library was simultaneously forged — retired, stabilized, demoted and mutated — under the fitness-driven lifecycle described in the paper. Most memory-augmented agents keep the library append-only. A skill that was correct at step 20 encodes a procedure the policy has outgrown by step 120, and it is still being retrieved into the context. SkillForge instead scores each skill against the policy's own rollouts and moves it between four states — trial, active, stable, retired — so the library and the model co-evolve. On WebShop this reaches 78.4% task success and 87.8…
Open weights
mit
7.6B parameters
32,768 tokens
transformers
This is the final SkillForge policy for ALFWorld: a full fine-tune of Qwen2.5-7B-Instruct trained with GRPO while its skill library was simultaneously forged — retired, stabilized, demoted and mutated — under the fitness-driven lifecycle described in the paper. Most memory-augmented agents keep the library append-only. A skill that was correct at step 20 encodes a procedure the policy has outgrown by step 120, and it is still being retrieved into the context. SkillForge instead scores each skill against the policy's own rollouts and moves it between four states — trial, active, stable, retired — so the library and the model co-evolve. On ALFWorld this reaches 92.4% overall success against…
Open weights
mit
7.6B parameters
32,768 tokens
transformers
