Can a shared-weight recurrent Transformer develop distinct internal roles without being partitioned into separate modules? We study this in Asymmetric Input Recurrence (AIR), a minimal two-state reasoning architecture in which the same Transformer model is reused for both updates (per literature, L and H) and the only built-in difference in the update rule is that the encoded input is injected during L-updates but not H-updates. Across Sudoku-Extreme and Maze, decoded rollouts reveal a consistent split: \zH behaves like a fully committed proposal state, whereas \zL retains local uncertainty and shifting intermediate structure. Freeze experiments show that this split is, in practice, related to the model's state dynamics: in Sudoku, freezing \zH reduces \zL's content changes whereas freezing \zL increases \zH's, while in Maze, freezing either state increases content changes in the other state. Ablations show that to induce specialization, the shared model needs to be able to tell the two update types apart, either from input injection asymmetry or from a separate level token. Mechanistically, attention analysis shows that L-updates are consistently more local than H-updates in both Sudoku and Maze. Together, these results show that, in a two-state recurrent setting, a clear state-identity signal can induce stable, related functional roles inside a shared-parameter recurrent Transformer. Code is available at \href{https://github.com/juchengshen/air}{\textcolor{blue}{https://github.com/juchengshen/air}}.
Do transformers, when trained on sequential reasoning traces, build internal models of the underlying task? And if so, does the structure of those internal representations mirror the structure of the domain? We train an 8-layer transformer on Sudoku solving traces and perform a mechanistic analysis of its internal computation. We establish two results. First, the model builds a substructure world model: it does not represent the board state cell by cell, as a human analyst would expect, but organizes information around the rows, columns, and boxes that Sudoku's constraints act on. Second, we identify a naked-single circuit: a small set of dedicated neurons in the final MLP layer, each individually detecting when exactly one digit remains possible for a specific cell, and reliably promoting that digit. These findings show that the geometry of an emergent world model is shaped by the constraint algebra of the domain, not its surface presentation, and that the resulting decision circuit is sparse, monosemantic, and fully interpretable. More broadly, they demonstrate that mechanistic interpretability tools can recover an end-to-end algorithmic account of how a transformer solves a combinatorial reasoning task.
We study learned memory tokens as a computational scratchpad for a single-block Universal Transformer with Adaptive Computation Time (ACT) on Sudoku-Extreme, a combinatorial reasoning benchmark. Memory tokens are empirically necessary: no configuration without them reaches non-trivial performance. The optimal count has a sharp lower threshold (T=0 always fails, T=8 reliably succeeds) followed by a stable plateau (T=8-32, 57.4% +/- 0.7% exact-match) and a dilution boundary at T=64. Under halt-side pressure (lambda warmup), mean halt drops monotonically with memory size across the plateau (from 11.6 at T=8 to 8.3 at T=64), showing that memory tokens and ponder depth substitute as resources at fixed accuracy. We also identify a router initialization trap that causes the majority of training runs to fail: both default zero-bias and Graves' recommended positive bias settle into a shallow halt equilibrium the model cannot escape. Inverting the bias to -3 ("deep start") eliminates the failure mode, and ablation shows the trap is inherent to ACT initialization rather than an artifact of our architecture. With reliable training, ACT yields an order of magnitude lower seed variance than fixed-depth processing (+/-0.7 vs +/-9.3 pp); lambda warmup recovers 34% of compute at matched accuracy; and attention heads specialize into memory readers, constraint propagators, and integrators across recursive depth. Code: https://github.com/che-shr-cat/utm-jax.
Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation is unfinished or has entered a persistently unsuccessful regime. We study the dynamics of completion in attention- and MLP-based Tiny Recursive Models (TRMs) on 1,000 hard Sudoku puzzles. Extending recurrence from the nominal 16 steps to 512 steps increases cumulative exact-solve accuracy from 59.2% to 87.5% for the attention model and from 74.4% to 91.9% for the MLP model, solving more than two-thirds of the puzzles unsolved in the nominal budget. Across both architectures, latent-state motion drops sharply after the first exact solution. Completed states are typically locally contractive along the trajectory direction, even though the same local Jacobian retains strongly expanding directions. We characterize this phenomenon as trajectory-conditioned anisotropic stability. Perturbation experiments confirm this directional stability across both models. The multi-step fate of the maximally expanding direction differs: it is absorbed within 16 steps in the attention model but persists longer in the MLP model. The anisotropic-stability pattern also holds for a second attention checkpoint. Together, these results distinguish nominal-budget failure from completed computation and identify a common dynamical signature of completion across two recurrent architectures.