Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
- Published
- Source
- arXiv
- Paper number
- 446
- Field
- AI / General
- arXiv ID
- 2606.18206
Key points
- It solves signal propagation problems that grow with loop depth by using pre-norm and residual scaling.
- It introduces fixed-point convergence through an end-to-end halting mechanism, so no external halting module is needed.
- It guarantees adaptive computation, with the number of iterations automatically adjusted to task difficulty.
- On Sudoku Extreme, it matches TRM performance with 10 percentage points higher accuracy and about 27 percent less compute.
- It shows consistent gains on combinatorial reasoning benchmarks such as Maze, state tracking, and ARC-AGI.
- It provides theoretical justification for the halting decision based on mathematical fixed-point theorems.
Paper links
External research summaries. These are not HDATF publications or measured product results.