Navigating Social Dilemmas with LLM-based Agents via Consideration of Future Consequences

Agents built on LLMs have shown versatile capabilities but face difficulties in being cooperative in social dilemma situations. When making decisions under the strain of selecting between long-term consequences and short-term benefits in commonly shared resources, LLM-based agents are vulnerable to the tragedy of the commons, i.e. individuals' greed exploitation leads to early depletion. We propose LLM agents that consider future consequences to aid them in navigating intertemporal social dilemmas. We introduce two approaches-prompting and intervention-to equip the agent with the ability to consider future consequences when making a decision, which results in a new kind of agent-CFC-Agent. Furthermore, we enable the CFC-Agent to act toward different levels of consideration for future consequences. Our experiments in different settings show that agents that consider future consequences exhibit sustainable behaviour and achieve high common rewards for the population.