I.
Distill the principles.
Draw on existing neuroscience research to identify computational mechanisms for learning, memory, and the coordination of search.
Advancing the state
of the art in AI
through neuroscience.
Voaige is an AI research lab translating insights from cognitive and systems neuroscience into computational principles for reasoning, memory, and search.
We are engineering these principles into LLMs under the constraint of building state-of-the-art,
commercially deployable systems.
Begin with Fixed Learning.
Fixed learning, recalled experiences, and live search form one coordinated system. An evaluated outcome is retained as a specific episode that can guide the next search; broader patterns can be learned over time.
Our research
From neuroscience to
high-performing AI systems.
We pursue two connected lines of research to build state-of-the-art,
commercially deployable systems.
II.
Engineer the systems.
Investigate the mechanics of large language models to turn those principles into algorithms and working systems.
Our guiding hypothesis
Intelligence is search.
Find useful actions, explanations, and solutions among many possibilities. Enumerate candidates, evaluate them, and select a promising path.
Cognition coordinates search.
Decide what to explore, what to recall, and when further computation is worth its cost. Bring learning, memory, and search into one coordinated system.
Memory makes search efficient.
Reuse prior discoveries to guide the next search. Retain useful experiences, recall them when relevant, and deliberate on what remains unresolved.
From hypothesis to system
Test Time
Cognition.
Our research, engineered into
the way AI reasons.
The TTC layer sits between the agent and the model, operating without modifying either. It is the site of inference-time computation: the cognitive architecture that governs how reasoning unfolds between input and output.
Explore Test Time CognitionAgent
Planning · Tools · Context
Voaige
Test Time Cognition
Search · Evaluate · Allocate effort
Model
Weights · Architecture · Training
Our Research Applied
- Tokens
- 307B
- Domains
- 3
- Agents
- 6
Customer Service
Test Time Cognition achieves SOTA performance.
55.3%Performance
- Baseline · Opus 5 from Sierra
- TTC: Qwen + Grok
Coding
Test Time Cognition achieves higher performance at lower cost.
+5.2 ppPerformance
38.5%Lower cost
- Baseline: GPT-5 · MiniMax
- TTC: GPT-5 + MiniMax
Financial Research
Test Time Cognition achieves higher performance at lower cost.
+13.0 ppPerformance
58.6%Avg. cost reduction
- Baseline: Kimi K3 · DeepSeek V4 Flash
- Same models + TTC
Join us
A unique place to work on the mission.
We bring together cognitive and systems neuroscientists, AI researchers, mathematicians, and engineers around a single shared challenge: to develop a coherent computational framework for cognition and memory, and test it in AI systems that push beyond the current frontier.
Join UsStay in the loop