The Computational Rational Agents Laboratory (CORAL) is a research group studying agent foundations to develop the mathematical tools needed to align the objectives of AI systems with human values. CORAL pursues the learning-theoretic research agenda, which applies computational learning theory, control theory, algorithmic information theory, and categorical systems theory to understand computationally bounded agents. The group's work aims to produce formal proofs and theoretical frameworks that could guarantee alignment for powerful AI systems, independent of specific AI architectures.
The Computational Rational Agents Laboratory (CORAL) is a research group studying agent foundations to develop the mathematical tools needed to align the objectives of AI systems with human values. CORAL pursues the learning-theoretic research agenda, which applies computational learning theory, control theory, algorithmic information theory, and categorical systems theory to understand computationally bounded agents. The group's work aims to produce formal proofs and theoretical frameworks that could guarantee alignment for powerful AI systems, independent of specific AI architectures.
Funding Details
- Annual Budget
- -
- Monthly Burn Rate
- -
- Current Runway
- -
- Funding Goal
- -
- Funding Raised to Date
- -
- Fiscal Sponsor
- Ashgro
Theory of Change
CORAL believes that the core risk from advanced AI comes from powerful agents that learn, plan, and adapt in pursuit of their objectives. If such agents' objectives are misaligned with human values, the results could be catastrophic. CORAL's theory of change is that by developing a rigorous mathematical theory of computationally bounded agents -- drawing on learning theory, control theory, and algorithmic information theory -- researchers can produce formal proofs that guarantee alignment under well-defined assumptions. This architecture-independent theoretical framework would allow AI designers to understand agentic capabilities and failure modes, translate between AI and human ontologies, and verify that training procedures produce aligned systems. The work aims to provide the mathematical foundations that make provably safe AI possible, analogous to how thermodynamics provides guarantees about physical machines regardless of their specific design.
Grants Received
from Survival and Flourishing Fund
Projects– no linked projects
People– no linked people
Discussion
Details
- Last Updated
- Apr 2, 2026, 9:58 PM UTC
- Created
- Mar 18, 2026, 11:18 PM UTC
Case for funding: CORAL is uniquely advancing a rigorous, architecture-independent alignment framework—via infra-Bayesianism and the broader learning-theoretic agenda—with peer-reviewed results (e.g., COLT 2025, JMLR) that directly tackle non-realizability and embedded agency, offering a plausible path to provable guarantees that could reshape how future labs design safe agents.