Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
Abstract
Equilibrium Reasoners enable scalable reasoning through task-conditioned attractors that guide latent dynamical systems toward valid solutions, achieving significant accuracy improvements through iterative test-time computation.
Scaling test-time compute by iteratively updating a latent state has emerged as a powerful paradigm for reasoning. Yet the internal mechanisms that enable these iterative models to generalize beyond memorized patterns remain unclear. We hypothesize that generalizable reasoning arises from learning task-conditioned attractors: latent dynamical systems whose stable fixed points correspond to valid solutions. We formalize this process through Equilibrium Reasoners (EqR), which enable test-time scaling without external verifiers or task-specific priors. EqR scales internal dynamics along two axes: depth, by running more iterations, and breadth, by aggregating stochastic trajectories from multiple initializations. Empirically, gains from test-time scaling are tightly coupled with stronger convergence toward solution-aligned attractors. This attractor perspective allows neural networks to adaptively allocate test-time compute based on task difficulty. While simple cases converge within 1 to 5 iteration steps, harder cases benefit from massive test-time scaling. By unrolling up to the equivalent of 40,000 layers, scalable latent reasoning boosts accuracy from 2.6% for feedforward models to over 99% on Sudoku-Extreme. These results suggest that learned attractor landscapes provide a useful mechanistic lens for understanding scalable reasoning in iterative latent models.
Community
nice video!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Solve the Loop: Attractor Models for Language and Reasoning (2026)
- Probabilistic Tiny Recursive Model (2026)
- Generative Recursive Reasoning (2026)
- LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models (2026)
- Stability and Generalization in Looped Transformers (2026)
- Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning (2026)
- Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2605.21488 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper