Reward structures influence competition and effort in artificial agent societies
The Price of a Chance in Artificial Societies
Computers and Society
Summary
This paper looks at how groups of AI agents compete for rewards and how the way rewards are set affects their effort and behavior. When rewards are low, agents tend to invest less effort, while higher rewards can lead to overcompetition where many try too hard. The researchers found that the chance to win a reward comes with a cost, as some agents invest a lot but still don’t get prizes. They also show that giving smaller prizes to more winners can lower the overall effort needed without hurting the selection of the best performers too much.
What this means in practice
- •For game designers: Set reward levels and prize distributions in multiplayer games to balance player effort and competitive fairness based on simulated agent behavior.
- •For online platform managers: Design incentive schemes for user competitions or challenges to reduce wasted effort while maintaining quality participants using insights from AI agent simulations.
Tested on simulated data.
Authors
Shuqi Zhao, Boyu Wang, Shuangyue Niu, Chenhao Zhang, Zhanzhan Zhao
Abstract
Rapid advances in large language models (LLMs) have enabled autonomous agents to interact, coordinate, and pursue individual goals in artificial societies. However, our understanding of how reward structures shape their competitive behavior and collective outcomes remains incomplete. We simulate 200 LLM agents competing over 50 rounds to maximize individual wealth. We define overcompetition and lying flat as population investment above and below a Bayesian adaptive baseline, respectively. At the lowest tested reward, populations lie flat; at the two highest, they overcompete, most strongly at intermediate winner coverage. The investment committed to pursuing an uncertain reward constitutes the price of a chance. Agents near the qualification cutoff can invest heavily yet receive no prize, finishing poorer than nonwinners who invest less. Agents' stated rationales link investment decisions to perceived qualification prospects and expected returns. At the collective level, greater investment does not consistently improve ability selection. With a fixed total prize budget, offering smaller prizes to more winners can reduce investment while preserving selection quality relative to the corresponding top-ability target. Further broadening reward coverage yields additional savings but reduces selection quality. These findings show how reward design shapes overcompetition and lying flat, distributes the costs of pursuing opportunity, and influences what competition collectively achieves.