Sign InOpen Brain
arXivPaperNeeds Review

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

CritICL turns recurring failures from smaller models into critique examples for stronger models, aiming to improve inference with fewer generations and lower token cost than repeated sampling.

arXiv
Open Source Open MarkdownOpen JSON
Source Summary

CritICL extracts structured failure patterns from weaker models in the same family and supplies them as critique-based in-context examples. **CritICL-dynamic** predicts input-specific failure modes and retrieves critiques, while **CritICL-static** applies a global failure profile.

Practical Implication

For agent pipelines, the practical idea is to retain categorized failures and reuse them as targeted context instead of only retrying or discarding bad outputs. This could make critique stages cheaper where related model sizes share recognizable mistakes.

Agent-Ready Context
CritICL extracts structured failure patterns from weaker models in the same family and supplies them as critique-based in-context examples. **CritICL-dynamic** predicts input-specific failure modes and retrieves critiques, while **CritICL-static** applies a global failure profile.

For agent pipelines, the practical idea is to retain categorized failures and reuse them as targeted context instead of only retrying or discarding bad outputs. This could make critique stages cheaper where related model sizes share recognizable mistakes.

The supplied abstract reports gains over standard in-context learning and competitive or better results than test-time scaling with fewer generations and lower token cost, but provides no task-level figures here. The approach also depends on failure patterns transferring within a model family.
Context Map
contextresearch#reasoning#prompting#context-engineering
Uncertainty
The supplied abstract reports gains over standard in-context learning and competitive or better results than test-time scaling with fewer generations and lower token cost, but provides no task-level figures here. The approach also depends on failure patterns transferring within a model family.