🛰️ Daily AI Frontier
‹ back to 2026-08-19

Recirculation

Research LLMs & Foundation Models

Ranking

Overall 82
Content 95
Popularity N/A

No observed public metrics; popularity remains neutral/archived.

Representative image for Recirculation

Merged summary

TL;DR - Recirculation adds inference-time recurrence to pretrained foundation models so they can iteratively update belief states without retraining. Adaptive recirculation substantially improves Gemma 3 perplexity and reasoning accuracy with essentially no added generation latency, though prefill becomes serial.

  • Recirculation addresses transformer depth limits by turning the model into a recurrent dynamical system for state tracking.
  • The method is distinct from chain-of-thought reasoning, depth looping, and training recurrent transformer architectures.
  • Adaptive recirculation freezes the original model weights and requires only light hyperparameter tuning.
  • On Gemma 3 models, it reduces perplexity by 23% across a dataset suite and increases GSM8K accuracy by 21% relative to off-the-shelf baselines.

Sources (1)

Recirculation

arXiv cs.LG Michael C. Mozer, Shoaib Ahmed Siddiqui, Danny Sawyer, Sunny Sanyal, Rosanne Liu 2026-08-18 arXiv:2608.17981
Public signals N/A
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-18 14:20:08.797298 UTC

TL;DR - Recirculation adds inference-time recurrence to pretrained foundation models so they can iteratively update belief states without retraining. Adaptive recirculation substantially improves Gemma 3 perplexity and reasoning accuracy with essentially no added generation latency, though prefill becomes serial.

  • Recirculation addresses transformer depth limits by turning the model into a recurrent dynamical system for state tracking.
  • The method is distinct from chain-of-thought reasoning, depth looping, and training recurrent transformer architectures.
  • Adaptive recirculation freezes the original model weights and requires only light hyperparameter tuning.
  • On Gemma 3 models, it reduces perplexity by 23% across a dataset suite and increases GSM8K accuracy by 21% relative to off-the-shelf baselines.
item →