#Reasoning Systems

3 articles with this tag

Argus: An Evolving AI Runtime
AI Research

Argus: An Evolving AI Runtime

Argus introduces a persistent, self-evolving AI runtime that enhances long-horizon reasoning, achieving significant benchmark improvements without model retraining.

3 months ago
Reasoning Beyond Linear Chains
AI Research

Reasoning Beyond Linear Chains

The Pyligent framework enables AI to learn complex reasoning by validating search paths and mastering backtracking from failures, outperforming imitation learning.

4 months ago
Attractors Unlock Scalable Reasoning
AI Research

Attractors Unlock Scalable Reasoning

Equilibrium Reasoners (EqR) leverage learned attractor landscapes to achieve scalable, adaptive test-time compute allocation, dramatically boosting accuracy on complex reasoning tasks.

5 months ago