SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However, its potential for post-training Large Language Models (LLMs) remains underexplored. We propose Self-Reflective Policy Optimization (SRPO), a framework that internalizes this capability. SRPO enables LLMs to analyze their own completed trajectories, synthesize errors into concise "reflection patches," and use reflection-conditioned teacher scores on student on-policy rollouts as dense token-level training signals. This process effectively transfo
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.
- LinkedLinked via arxiv author · 85%Jialong Liu →
“SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning”
- LinkedLinked via arxiv author · 85%Yuling Shi →
“SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning”
- LinkedLinked via arxiv author · 85%Ning Yang →
“SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning”
- LinkedLinked via arxiv author · 85%Xiaodong Gu →
“SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning”
- LinkedLinked via arxiv author · 85%Zuchao Li →
“SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning”
- FuzzySimilar title/name (fuzzy) · 84%Thysrael/Horizon →
“Fuzzy title match (0.92): “SRPO: Self-Reflective Policy Optimization for Long-Horizon R” ≈ “Thysrael/Horizon””
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”