aiqbench analysis
This research introduces Representational Empowerment (RepEmp), a novel principle for continual model construction that prioritizes the strategic curation of internal representations over mere fidelity to external states. By leveraging an LLM-augmented architecture, the study demonstrates that agents using RepEmp achieve superior cross-task transfer and structure recovery compared to traditional exploration-based methods. This work offers critical insights into optimizing resource-constrained learning systems by defining what is worth representing in dynamic environments.
What Is Worth Representing? Representational Empowerment for Continual Model Construction
arXiv:2609.02322v1 Announce Type: new Abstract: The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at all. We frame this problem as continual model construction: an agent maintains an environment-specific model M of an inaccessible world W and curates a persistent library L of reusable representational elements across environments. We propose Representational Empowerment (RepEmp) to score candidate elements by how much they expand the agent's future capacity to model and plan, complementing the classic definition of empowerment, but redefined as control over internal representations instead of external states. We realize the framework as a hierarchical Curator-Actor architecture and test it across three experiments. In a closed-vocabulary causal-learning task, human participants construct causal models at varying abstraction granularities to maximize goal reachability rather than fidelity to the world, a signature better predicted by RepEmp than by information-gain alternatives. Matched simulations reveal that RepEmp-guided construction contributes more than exploration to sufficient structure recovery and cross-task transfer. Finally, in an open-vocabulary planning domain, an LLM-augmented Curator builds more compact symbolic libraries, which also generalize better than baselines. Ablating RepEmp eliminates these benefits. Together, these results identify RepEmp as a key principle for continual model construction: deciding what to build, retain, and reuse under bounded resources.
Title:What Is Worth Representing? Representational Empowerment for Continual Model Construction
Abstract:The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at all. We frame this problem as continual model construction: an agent maintains an environment-specific model M of an inaccessible world W and curates a persistent library L of reusable representational elements across environments. We propose Representational Empowerment (RepEmp) to score candidate elements by how much they expand the agent's future capacity to model and plan, complementing the classic definition of empowerment, but redefined as control over internal representations instead of external states. We realize the framework as a hierarchical Curator-Actor architecture and test it across three experiments. In a closed-vocabulary causal-learning task, human participants construct causal models at varying abstraction granularities to maximize goal reachability rather than fidelity to the world, a signature better predicted by RepEmp than by information-gain alternatives. Matched simulations reveal that RepEmp-guided construction contributes more than exploration to sufficient structure recovery and cross-task transfer. Finally, in an open-vocabulary planning domain, an LLM-augmented Curator builds more compact symbolic libraries, which also generalize better than baselines. Ablating RepEmp eliminates these benefits. Together, these results identify RepEmp as a key principle for continual model construction: deciding what to build, retain, and reuse under bounded resources.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.02322 [cs.LG]
(or arXiv:2609.02322v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.02322 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 317 words
Related coverage
Deconfusing Corrigibility
AI Alignment Forum · Oct 17, 2026
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
The user in the LLM might be a moral patient too (a strange implication of the PSM and simulators)
LessWrong · Oct 15, 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026