arXiv AI

Autonomy, Social Norms, and Alignment: Towards a Developmental Framework for Autonomous Artificial Agents

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.

arXiv AI
Oct 19

Darwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving Agents

Darwin‑Claw is a new framework for large language model agents that enables environment‑adaptive, self‑evolving behavior. It systematically distills episodic experiences into prototype vectors through a hierarchical experience consolidation system, providing context‑sensitive perception patches and explicit optimization signals for skill refinement. The method is deployable with mainstream agent systems and, according to experiments on WildClawBench, delivers significant performance gains while maintaining controllability and stability.

By Mingze Yin, Xiaohan Wang, Dian Li, Longfei Luo, Jiahong Yan, Yiheng Zhu, Chang-Yu Hsieh
arXiv AI
Sep 28

Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence

The article discusses autonomous systems as the pinnacle of AI development, emphasizing the need to blend connectionist and symbolic AI within systems engineering. It introduces a generic agent architecture that organizes behavior around long‑term memory and outlines challenges in linking sensory data to structured memory, goal‑oriented decision making, planning, and agent coordination for collective intelligence. The authors also explore agent trustworthiness, noting it extends beyond behavior to include cognitive validity, and propose methods for its evaluation while highlighting the gap between current capabilities and the envisioned autonomous multi‑agent systems.

By Joseph Sifakis
arXiv AI
3d ago

Open Challenges and Opportunities in Human-Agent Systems

The paper "Open Challenges and Opportunities in Human-Agent Systems" discusses how agentic AI systems increasingly perform extended tasks on behalf of people, making human‑agent interaction essential. It reviews computational approaches—such as Theory of Mind, belief‑desire‑intention models, goal and plan recognition, observer‑aware planning, and cooperative inverse reinforcement learning—that help agents understand human perspectives, coordinate complementary capabilities, and maintain productive relationships in socio‑technical environments. The authors argue that progress requires treating human interaction as an ongoing decision problem shaped by uncertainty, interdependence, and potentially conflicting objectives.

By Reuth Mirsky, Sarath Sreedharan, Nitay Alon, Stefan Sarkadi, Munindar P. Singh, Liz Sonenberg, Peter Stone, Silvia Tulli, Stylianos Loukas Vasileiou, Shlomo Zilberstein
arXiv AI
Oct 9

Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs

The paper introduces the concept of normative competence for large language models (LLMs), defined as the ability to infer community norms from interaction rather than static knowledge. Using a multi‑agent debate environment governed by synthetic norms, the authors show that baseline LLMs fail to learn norms even when it improves accuracy, and that adding normative modules yields highly sensitive, non‑generalizable results. The study also reveals that LLMs indiscriminately copy idiosyncratic, non‑normative behaviors, indicating a failure to distinguish enforced rules from noise.

By Andrea Wynn (Nathan), Harsh Satija (Nathan), Seokhyun (Nathan), Baek, Anqi Liu, Eric Nalisnick, Gillian K. Hadfield
arXiv AI
Jun 12

From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence

arXiv:2601. 21570v2 Announce Type: replace Abstract: The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection.

By Zixing Lei, Genjia Liu, Yuanshuo Zhang, Qipeng Liu, Yuzhu Cai, Sixiang Chen, Jixian Wu, Yunhong Wang, Weixin Li, Chuan Wen, Bo Zhao, Shanghang Zhang, Wenzhao Lian, Siheng Chen