# A Persistent State for Auditable Mixture-of-Experts Routing

arXiv: https://arxiv.org/abs/2609.34634 · HTML: https://mlsanity.com/paper/2609.34634/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 17 of 17)

- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [The Stack: 3 TB of permissively licensed source code](https://mlsanity.com/paper/2211.15533/) (2022)
- [Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints](https://mlsanity.com/paper/2212.05055/) (2022)
- [Multilingual Routing in Mixture-of-Experts](https://mlsanity.com/paper/2510.04694/) (2025)
- [Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization](https://mlsanity.com/paper/2502.19261/) (2025)
- [Mixture of Experts Made Intrinsically Interpretable](https://mlsanity.com/paper/2503.07639/) (2025)
- [Layerwise Recurrent Router for Mixture-of-Experts](https://mlsanity.com/paper/2408.06793/) (2024)
- [Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts](https://mlsanity.com/paper/2604.08541/) (2026)
- [Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis](https://mlsanity.com/paper/2505.24593/) (2025)

## Abstract (arXiv)

Mixture-of-Experts (MoE) models repeatedly route tokens to sparse subsets of experts, but conventional routers expose no routing-specific record of how cross-layer influences accumulate. We introduce Scratchpad-Augmented Mixture-of-Experts (SA-MoE), which gives each router access to a low-dimensional persistent state that is not provided to the experts. Learned layerwise writes update this state, and their realized post-update changes exactly decompose the state-mediated contribution to any later routing margin, forming a routing ledger. Across sparsely upcycled SmolLM2- and Gemma-based models and three independent training seeds per architecture, this pathway adds less than 1% analytical forward compute and is strongly used by trained routers: local removal of its router contribution changes the selected Top-2 expert set in 87.6% and 69.9% of decisions, respectively. Relative to a matched latest-write-only control, persistent accumulation increases long-horizon future-routing accessibility by 19.4 and 12.2 percentage points, with positive effects in every seed. More than 90% of absolute ledger contribution comes from non-recent writes in both families, and full-forward suppression of ledger-selected writes changes later routing and output distributions. The ledger is an exact provenance object for the persistent-state pathway, not a complete causal explanation of routing. Sensitivity-aware scores better predict full-forward intervention effects, and post-hoc methods recover related cross-layer attribution without architectural modification. SA-MoE instead makes one routing-specific computational history explicit and directly inspectable within the model's natural forward computation.