arXiv AI By Arin Mukhopadhyay, Aris Filos-Ratsikas, Panayiotis Danassis

The Delegation Dilemma: Economies of Scale, Accountability, and Polycentric Governance

Read the original on arXiv AI →

The paper examines how collective‑action systems balance decentralization and centralization through delegation. A reduced‑form model shows a scale–accountability tradeoff: larger constituencies lower individual costs but reduce a center’s incentive to retain each member, limiting non‑exploitative delegation to an endogenous size. Simulations with large language model agents reveal that polycentric governance structures naturally arise, cycling through concentration, exploitation, exit, and re‑formation, and that different model capacities vary in their willingness to lead and in their propensity to exploit.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Jun 9

Payoff scaling shapes cooperation in LLM agents across languages

arXiv:2601. 19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users.

By Trung-Kiet Huynh, Dao-Sy Duy-Minh, Thanh-Bang Cao, Phong-Hao Le, Hong-Dan Nguyen, Phu-Quy Nguyen-Lam, Minh-Luan Nguyen-Vo, Hong-Phat Pham, Phu-Hoa Pham, Thien-Kim Than, Chi-Nguyen Tran, Huy Tran, Gia-Thoai Tran-Le, Alessio Buscemi, Le Hong Trang, The Anh Han
arXiv AI
Oct 15

Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes

The paper introduces Degrees of Freedom (DoF), a continuous framework that measures how much decision-making is delegated to agents in large language model–based multi‑agent systems. By varying DoF, the authors explore a spectrum between fully centralized and fully decentralized coordination, finding that intermediate settings often outperform both extremes across several task domains. The study shows that task characteristics and retained experience influence how coordination granularity affects performance, offering empirical guidance for designing hybrid coordination regimes.

By Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu, Yi Han, Yangyang Zheng, Hao Wang, Qian Li, Chengwei Qin