# Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching

arXiv: https://arxiv.org/abs/2608.09444 · HTML: https://mlsanity.com/paper/2608.09444/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 51 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 30 of 41)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [Mixture-of-Depths: Dynamically allocating compute in transformer-based language models](https://mlsanity.com/paper/2404.02258/) (2024)
- [Depth-Adaptive Transformer](https://mlsanity.com/paper/1910.10073/) (2019)
- [PonderNet: Learning to Ponder](https://mlsanity.com/paper/2107.05407/) (2021)
- [Scaling Latent Reasoning via Looped Language Models](https://mlsanity.com/paper/2510.25741/) (2025)
- [Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation](https://mlsanity.com/paper/2507.10524/) (2025)
- [SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference](https://mlsanity.com/paper/2307.02628/) (2023)
- [Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding](https://mlsanity.com/paper/2310.05424/) (2023)
- [Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA](https://mlsanity.com/paper/2410.20672/) (2024)
- [EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism](https://mlsanity.com/paper/2312.04916/) (2023)
- [LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation](https://mlsanity.com/paper/2602.11451/) (2026)
- [Parcae: Scaling Laws For Stable Looped Language Models](https://mlsanity.com/paper/2604.12946/) (2026)
- [Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers](https://mlsanity.com/paper/2604.07822/) (2026)
- [Sparse Universal Transformer](https://mlsanity.com/paper/2310.07096/) (2023)
- [CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference](https://mlsanity.com/paper/2310.10845/) (2023)
- [How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models](https://mlsanity.com/paper/2604.21106/) (2026)
- [Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning](https://mlsanity.com/paper/2602.07845/) (2026)
- [Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning](https://mlsanity.com/paper/2511.08577/) (2025)

## Built on by (most cited first, 6 of 6)

- [Improving Test-Time Scaling with Adaptive Looped Transformers](https://mlsanity.com/paper/2609.35748/) (2026)
- [FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL](https://mlsanity.com/paper/2609.34488/) (2026)
- [Shallow Queries, Mature Values: Depth-Asynchronous Self-Speculation for Looped Transformers](https://mlsanity.com/paper/2609.34538/) (2026)
- [LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation](https://mlsanity.com/paper/2609.39740/) (2026)
- [Towards Looped Models Done Right, Part II: Rethinking at Fixed Points](https://mlsanity.com/paper/2610.06833/) (2026)
- [One Model to Loop Them All: Elastic Latent Recurrence for Language Models](https://mlsanity.com/paper/2610.12582/) (2026)

## Abstract (arXiv)

A main promise of looped language models is depth-adaptive inference. By looping a block of shared layers a variable number of times, the model can use less compute for "easy" tokens and more for "hard" ones. However, tokens with different numbers of loops cannot share a uniform forward pass and therefore cannot be handled by standard batching systems such as vLLM. The practical value of depth-adaptive inference thus hinges on whether batching can be made efficient. We introduce the first efficient method for depth-adaptive looped LMs via continuous depth batching (CDB), which forms new batches between loop steps. Our method dynamically schedules looped and non-looped parts of the architecture, manages looped KV-caching, and predicts which tokens will exit the loop in advance so it can prepare batches asynchronously. Experiments on Ouro 1.4B and Huginn 3.5B show that fully looped architectures are best suited to depth-adaptive inference, as large non-looped layers outside the recurrent core (e.g., token embedding, LM head, and unshared transformer blocks) slow down and complicate scheduling. Overall, CDB realizes up to 99% of the estimated maximum speedup available, leaving further gains primarily dependent on model architecture and exit behavior.