Skip to content

DARPA – Methodological Advancements for Generalization Insights into Complex Systems (MAGICS) – DARPA-EA-25-02-05

Home / Funding Opportunity / DARPA – Methodological Advancements for Generalization Insights into Complex Systems (MAGICS) – DARPA-EA-25-02-05

DARPA – Methodological Advancements for Generalization Insights into Complex Systems (MAGICS) – DARPA-EA-25-02-05

twitterlinkedin

DARPA’s Defense Sciences Office is seeking submissions of abstracts for innovative exploratory research concepts in the technical domain of computational science research in complex, dynamic, evolving systems.

This opportunity is soliciting ideas to explore the question: Are there new methods and paradigms for modeling collective human behavior capable of overcoming limits of statistical approaches to accurately predict complex social phenomena and capture the dynamics of evolving, open, time varying, recursive, reactive, non-ergodic systems?

Ultimately, the goal is to spur the development of novel, rigorous methods and frameworks that advance our collective capacity to understand and predict human behavior with greater accuracy and nuance.

Despite the explosion of digital data streams and powerful new machine learning tools, current statistical methods cannot create models that remain valid when applied to evolving, open, time varying, recursive, reactive, non-ergodic systems. The limitations of current methods for modeling human systems have revealed fundamental constraints on the ability to model and forecast human behavior in complex systems, and addressing these challenges requires overcoming several significant challenges that large data sets and ML do not address.

Areas of interest include:

  • data inference boundaries and limitations
  • alignment validation limitations
  • adaptation ;imitations and model obsolescence
  • psychosocial domain limitations
  • complex phenomena

Proposers must work with open-world systems and data sets.  Proposals that incorporate theoretical, computational, and empirical efforts by integrating disciplines such as psychometrics, behavioral science, data science, and machine learning are within scope.

Between USD$100,000 – $300,000 is available for projects of up to 12 months, with an FTE effort of approximately 1 person over that period.

The call is issued under the Advanced Research Concepts Exploration Announcement DARPA-EA-25-02.

Abstracts are due 10 July 2025.

 

Read more

Documents

ARC Opportunity – MAGICS: DARPA-EA-25-02-05

EA Master Solicitation for ARC: DARPA-EA-25-02

You may be also interested in ...