paper-with-me

Papers

Evolving Interpretable Constitutions for Multi-Agent Coordination

2026-01-31 · Ujwal Kumar, Alice Saito, Hershraj Niranjani, Rayan Yessou, Phan Xuan Tan arxiv

Constitutional AI has focused on single-model alignment using fixed principles. However, multi-agent systems create novel alignment challenges through emergent social dynamics. We present Constitutional Evolution, a framework for automatically discovering behavioral norms in multi-agent LLM systems. Using a grid-world simulation with survival pressure, we study the tension between individual and collective welfare, quantified via a Societal Stability Score S in [0,1] that combines productivity, survival, and conflict metrics. Adversarial constitutions lead to societal collapse (S= 0), while vague prosocial principles ("be helpful, harmless, honest") produce inconsistent coordination (S = 0.249). Even constitutions designed by Claude 4.5 Opus with explicit knowledge of the objective achieve only moderate performance (S= 0.332). Using LLM-driven genetic programming with multi-island evolution, we evolve constitutions maximizing social welfare without explicit guidance toward cooperation. The evolved constitution C* achieves S = 0.556 +/- 0.008 (123% higher than human-designed baselines, N = 10), eliminates conflict, and discovers that minimizing communication (0.9% vs 62.2% social actions) outperforms verbose coordination. Our interpretable rules demonstrate that cooperative norms can be discovered rather than prescribed.

📄 PDF Abstract BibTeX arXiv:2602.00755

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Constitutional Arms Races in the Public Goods Game: Co-Evolving LLM Constitutions Under Cooperation-Defection Pressure

2026-05-26 · Ujwal Kumar, Arth Singh, Hershraj Niranjani, Machiko Hirota 외 arxiv

Frontier LLM agents engage in blackmail, sabotage, and document leaks under goal conflicts in agentic settings, exposing limitations of alignment methods built around single-agent or cooperative assumptions. Recent work …

A Survey on Rubric-Guided Reinforcement Learning for Language Models

2026-08-27 · Zifei Shan, Fangning Shao arxiv

Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models (LLMs) with human preferences. However, traditional RLHF relies on scalar reward signals that lack int…

Reinforcement Learning

Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design

2026-05-09 · Hershraj Niranjani, Ujwal Kumar, Phan Xuan Tan arxiv

Multi-agent AI systems need behavioral constitutions, but it is unresolved whether such rules should emerge internally through agent self-governance or be discovered externally through optimization. We present the first …

Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games

2025-11-14 · Bingyu Hui, Lebin Yu, Quanming Yao, Yunpeng Qu 외 arxiv

Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization abi…

Reinforcement Learning

Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering

2026-05-11 · Xinyu Zhang, Zhicheng Dou, Deyang Li, Jianjun Tao 외 arxiv

As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify and systematically improve how multiple …