Asymmetric Capacity Allocation in Self-Refinement Pipelines
Self-refinement, typically structured as generation, critique, and revision, is a widely adopted paradigm for improving LLM generation and serves as a core mechanism in many LLM agents. While the three stages involve different cognitive demands, most existing approaches conveniently treat the model size as an implementation detail rather than a subject of study, which may lead to a waste of resources. Little work has systematically examined how model size affects each stage or whether effective self-refinement requires equally capable models for generation, critique, and revision. We present t
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.
- PossiblePossibly related (embedding) · 51%AI’s recursive self-improvement might not come so quickly after all →
- PossiblePossibly related (embedding) · 47%A system-level approach to prompt injection: separating instruction and data channels in LLM agents [P] →
- PossiblePossibly related (embedding) · 46%Why Self-Correction Loops Can Degrade Reliability in LLM Pipelines (85% Down to 62%) →
- PossiblePossibly related (embedding) · 46%IEEE Rolls Out Large Language Models Virtual Training Course →
- LinkedLinked via arxiv author · 85%Zhuoyi Yang →
“Asymmetric Capacity Allocation in Self-Refinement Pipelines”
- LinkedLinked via arxiv author · 85%Ian G. Harris →
“Asymmetric Capacity Allocation in Self-Refinement Pipelines”
- LinkedLinked via arxiv author · 85%Salar Hashemitaheri →
“Asymmetric Capacity Allocation in Self-Refinement Pipelines”
- LinkedLinked via arxiv author · 85%Cassie Huang →
“Asymmetric Capacity Allocation in Self-Refinement Pipelines”