SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents
Large language model (LLM) agents are trained with reinforcement learning (RL) for complex decision-making tasks. However, most RL-trained agents remain episodic and cannot accumulate reusable knowledge across episodes. Recent skill-based approaches, such as SkillRL, attempt to address this issue by extracting skills from raw trajectories, but treat the skill bank as an append-only repository without verifying whether stored skills remain effective. In this paper, we propose SkillForge, a framework for continuous skill evolution that enables skills to be verified and refined through environmen
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%CodeForge-15B →
“Fuzzy title match (0.94): “SkillForge: Evolving Verifiable Skills for Reinforcement Lea” ≈ “CodeForge-15B””
- FuzzySimilar title/name (fuzzy) · 87%NirDiamant/GenAI_Agents →
“Fuzzy title match (0.94): “SkillForge: Evolving Verifiable Skills for Reinforcement Lea” ≈ “NirDiamant/GenAI_Agents””
- FuzzySimilar title/name (fuzzy) · 84%Unity-Technologies/ml-agents →
“Fuzzy title match (0.92): “SkillForge: Evolving Verifiable Skills for Reinforcement Lea” ≈ “Unity-Technologies/ml-agents””
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzySimilar title/name (fuzzy) · 59%Eigenwise/atomic-agents →
“Fuzzy title match (0.73): “SkillForge: Evolving Verifiable Skills for Reinforcement Lea” ≈ “Eigenwise/atomic-agents””
- LinkedLinked via arxiv author · 85%Shidong Yang →
“SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents”
- LinkedLinked via arxiv author · 85%Ziyu Ma →
“SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents”