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.
A radial search forest with cognition at its root. For three related problems in turn, learned priors narrow the search to one region, memory recalls the closest past route, and explicit search tries the branches that remain and selects a path. Each result is retained as a memory, so the second search tries far fewer branches than the first, and the third fewer still. The memories are then consolidated into learned priors.
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.
Engineer the systems.
Investigate the mechanics of large language models to turn those principles into algorithms and working systems.
Our Guiding Scientific Hypotheses
Intelligence is search.
Intelligence is the process of searching among possible actions, explanations, and solutions in pursuit of a goal. It involves generating and evaluating candidates, validating them against evidence, and pursuing promising paths.
Cognition coordinates search.
Cognition is the coordination of search over time. As a problem unfolds, it brings learned knowledge, memory, and exploration together to decide where to search, how to evaluate possibilities, and when to continue, change direction, or stop.
Memory makes search more efficient.
Memory is the retention and retrieval of experience that allows previous computation to be reused. It can guide and narrow search, resume it from a useful earlier point, or supply a known solution that bypasses explicit search.
Learning is getting faster, better, and cheaper at search.
Learning is the process by which experience improves a system’s ability to search. It can improve the quality and reliability of solutions, expand the range of problems the system can solve, and reduce the time and computation required.
From hypothesis to system
Test Time
Cognition.
Our research, engineered into
the way AI reasons.
The TTC inference layer is what the agent interacts with. The model weights sit inside it, and TTC directs the inference. It is the site of inference-time computation: the cognitive architecture that governs how reasoning unfolds between input and output.
Explore Test Time CognitionOur Research Applied
- tokens used for evals
- 307B
- use cases evaluated on
- 3
- agents tested
- 6
Customer Service
Test Time Cognition achieves SOTA performance.
55.3%Performance
- Baseline · Opus 5 from Sierra
- TTC: Qwen + Grok
TTC = Test Time Cognition
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
TTC = Test Time Cognition
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
TTC = Test Time Cognition
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