The paper introduces a scalable method for maximizing empowerment, defined as the number of executable skills an agent can perform from a given state. By linking skill learning to empowerment, the authors provide a recipe that works with any underlying skill learning approach, enabling large‑scale studies beyond traditional tabular settings. Experiments demonstrate that maximizing empowerment leads to emergent behaviors such as resource gathering, environment modification, and even building a house in the game Crafter.
By Catherine Ji, Vivek Myers, Joshua Lin, Alexandra Wingate, Sergey Levine, Benjamin Eysenbach
arXiv:2604.21155v2 Announce Type: replace
Abstract: Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an...
By Tristan Shah, Ilya Nemenman, Daniel Polani, Stas Tiomkin
The paper introduces a Bellman optimality equation for optimizing plasticity in Markov decision processes, extending recent work that reframes the stability‑plasticity dilemma as an empowerment‑plasticity tradeoff. It builds on Abel et al. (2025), which defined plasticity as the generalized directed information from observations to actions and empowerment as the reverse. This work is the first to address plasticity optimization under that new definition, providing a theoretical foundation similar to existing empowerment‑based approaches.
By Jeremy Lucas, Doina Precup
arXiv:2511. 04177v2 Announce Type: replace Abstract: Personal AI agents are increasingly deployed in shared environments, where their actions affect not just the primary user they are assisting, but bystanders who never consented to being affected by the system.
By Claire Yang, Claire Jie Zhang, Maya Cakmak, Max Kleiman-Weiner
The paper proposes a developmental framework for autonomous artificial agents that emphasizes learning social norms and alignment through direct interaction with dynamic environments. It argues that intrinsic motivations such as curiosity and competence can guide exploration, but also complicate alignment with human goals. By drawing parallels to child development, the authors suggest that regulatory sandboxes serve as pedagogical spaces where agents gradually acquire moral agency and adapt their behaviors through experience and cooperation.
By Marica Notte, Ludovica Marinucci, Vieri Giuliano Santucci
arXiv:2608. 08240v1 Announce Type: new Abstract: This paper explores the idea of promoting well-being and safety in human-AI interactions by forcing AI agents explicitly to empower humans and to manage the power balance between humans and AI agents in a desirable way.
By Jobst Heitzig, Ram Potham
arXiv:2512. 09831v2 Announce Type: replace Abstract: This paper develops a geometric framework for modeling concepts, motivation, and influence across cognitively heterogeneous agents.
By Chainarong Amornbunchornvej
arXiv:2609.17325v1 Announce Type: new
Abstract: Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organi...
By Anatoly Belikov
The paper investigates how transformers can possess a world model despite exhibiting behavioral failures. Using TaxiGPT, a transformer trained on random Manhattan walks, the authors show that the model internally represents intersections, streets, and its position, and uses a goal compass for navigation. They attribute failures to interference between overlapping intersection features and demonstrate that affordance packing mitigates these errors, concluding that world‑modeling abilities emerge at distinct training stages and should be studied mechanistically rather than merely observed behaviorally.
By Pierre Beckmann, Matthieu Queloz, Andre Freitas
arXiv:2506. 01692v2 Announce Type: replace Abstract: Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values.
By Sylee Dandekar, Shripad Deshmukh, Frank Chiu, W. Bradley Knox, Scott Niekum
The paper introduces Representational Empowerment (RepEmp), a metric for selecting representational elements that enhance an agent’s future modeling and planning abilities. Using a hierarchical Curator-Actor architecture, RepEmp is tested in three experiments: a closed‑vocabulary causal‑learning task, simulations showing improved structure recovery and transfer, and an open‑vocabulary planning domain where an LLM‑augmented Curator builds compact symbolic libraries. Ablation studies confirm that RepEmp is essential for these gains, positioning it as a key principle for continual model construction under resource constraints.
By Fei Dai, Hanqi Zhou, Alison Gopnik, Charley Wu
The paper introduces AGORA, a framework that independently varies team composition and interdependence structures to study how social scaffolding influences the evolution of large language model agents. Experiments across web search, codebase understanding, and document QA show that appropriate scaffolding can outperform a strong agent evolved alone by up to 25 points, primarily by empowering the most capable member to lead while others step back. The findings suggest that designing a self‑evolving multi‑agent system requires careful consideration of its social scaffolding to shape learning dynamics and leadership emergence.
By Seojin Hwang, Youngmin Choi, Hwanhee Lee