Research

We publish our work openly. Every paper is a step toward AI that is more efficient, more accessible, and safer for everyone.

Publications

Papers

May 29 2026

CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models

Mistyoz AI

Large language models have achieved strong reasoning capabilities, though often at the cost of massive parameter counts and expensive inference. In this work, we explore a different direction: adaptive reasoning depth in compact language models.

We present CosmicFish-HRM, a compact language model built around a Hierarchical Reasoning Module (HRM) that dynamically allocates reasoning compute during inference. Instead of applying fixed computation to every input, the model iterates through high-level and low-level reasoning cycles and learns when to halt based on input complexity.

Our results show that the model learns non-uniform reasoning behavior, allocating different numbers of reasoning steps across tasks and inputs. These findings suggest that adaptive reasoning depth may offer a promising alternative to relying solely on parameter scale for reasoning capability.

Hierarchical Reasoning Module

High-level and low-level reasoning cycles with learned halting.

Adaptive Compute

Dynamic step allocation based on input complexity, not fixed depth.

Compact Scale

Designed to run efficiently at small parameter counts, without sacrificing reasoning quality.

Our Commitment

Research that moves AI forward for everyone.

We will continue to do further research to improve AI, make it accessible, and make it safe. Every paper we publish is shared openly so the broader community can build on it.

Our research focuses on the areas where we believe the field needs more work: efficient architectures that run on consumer hardware, adaptive compute that scales with complexity, and safety systems that protect users without sending their data to the cloud.

Efficiency

Building models that do more with less. Compact architectures that run on your device without needing a data center.

Accessibility

Open weights, open research. AI that anyone can use, study, and build on, regardless of resources or geography.

Safety

Moderation and alignment research that protects users. Safety systems that work offline, without exposing private data.