The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game
As AI agents become increasingly capable of tool use and long-horizon tasks, they have begun to be deployed in settings where multiple agents can interact. However, whereas prior work has mostly focused on human-AI interactions, there is an increasing need to understand AI-AI interactions. In this paper, we adapt the iterated public goods game, a classic behavioral economics game, to analyze the behavior of four reasoning and non-reasoning models across two conditions: models are either told they are playing against "another AI agent" or told their opponents are themselves. We find that, across different settings, telling LLMs that they are playing against themselves significantly changes their tendency to cooperate. While our study is conducted in a toy environment, our results may provide insights into multi-agent settings where agents "unconsciously" discriminating against each other could inexplicably increase or decrease cooperation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Coalition-structured governance improves cooperation to provide public goods
While the benefits of common and public goods are shared, they tend to be scarce when contributions are provided voluntarily. Failure to cooperate in the provision or preservation of these goods is fundamental to sustain…
Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design
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 …
Altruism Design in Networked Public Goods Games
Many collective decision-making settings feature a strategic tension between agents acting out of individual self-interest and promoting a common good. These include wearing face masks during a pandemic, voting, and vacc…
Decision MakingA Flexible Design for Funding Public Goods
We propose a design for philanthropic or publicly-funded seeding to allow (near) optimal provision of a decentralized, self-organizing ecosystem of public goods. The concept extends ideas from Quadratic Voting to a fundi…
PhilosophyThe Role of Valence and Meta-awareness in Mirror Self-recognition Using Hierarchical Active Inference
The underlying processes that enable self-perception are crucial for understanding multisensory integration, body perception and action, and the development of the self. Previous computational models have overlooked an e…