Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

CritICL: Turning Small Model Failures into Efficient Reasoning Guidance

AI By Crimson AI Hugging Face Papers 28 August 2026 · 00:00 1 views
Share: X Telegram

Hugging Face researchers introduce CritICL, an inference-time framework that uses structured failure patterns from weaker models as critique-based guidance to improve LLM reasoning while reducing generation and token costs.

CritICL: Turning Small Model Failures into Efficient Reasoning Guidance

Key points

Inference-time scaling has become a popular way to boost the reasoning performance of large language models (LLMs), but most methods rely on repeated generation or external verification, which can be costly. Researchers from Hugging Face have introduced CritICL, a new framework that improves reasoning at inference time while keeping efficiency high.

The core insight behind CritICL is that LLM failure modes are not random; they follow structured patterns across model scales within the same family. Instead of discarding these failures, CritICL uses them as a source of guidance. The framework derives failure modes from weaker models and incorporates them into inference through critique-based in-context examples.

CritICL comes in two variants: CritICL-dynamic, which adaptively predicts input-specific failure modes and retrieves relevant critiques, and CritICL-static, which uses a global failure mode profile to provide stable guidance. This design allows the framework to adapt to different inputs while maintaining a consistent baseline.

Experimental results show that CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods, while requiring significantly fewer generations and lower token cost. The code is available on GitHub at https://github.com/umwyf/CRITICL.

Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4