{"ID":2889419,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22255","arxiv_id":"2507.22255","title":"Agent-centric learning: from external reward maximization to internal knowledge curation","abstract":"The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack adaptability. We propose representational empowerment, a new perspective towards a truly agent-centric learning paradigm by moving the locus of control inward. This objective measures an agent's ability to controllably maintain and diversify its own knowledge structures. We posit that the capacity -- to shape one's own understanding -- is an element for achieving better ``preparedness'' distinct from direct environmental influence. Focusing on internal representations as the main substrate for computing empowerment offers a new lens through which to design adaptable intelligent systems.","short_abstract":"The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack adaptability. We propose representational empowerment, a new perspective towards a truly ag...","url_abs":"https://arxiv.org/abs/2507.22255","url_pdf":"https://arxiv.org/pdf/2507.22255v1","authors":"[\"Hanqi Zhou\",\"Fryderyk Mantiuk\",\"David G. Nagy\",\"Charley M. Wu\"]","published":"2025-07-29T22:09:35Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.SC\"]","methods":"[]","has_code":false}