Abstract:Ensuring that AI agents behave safely and beneficially when interacting with other parties has emerged as one of the central challenges of modern AI safety. While mechanism design, as the theory of designing rules to align individual and collective objectives, can incentivize cooperative behavior, it is still an open question whether it alone is sufficient to maximize LLM agents' social welfare. This work proves that the answer is negative: drawing from incomplete contract theory, we formally show that when contracts cannot distinguish all relevant future contingencies, there is a strictly positive welfare loss that no realistic mechanism can eliminate. We show that prosocial agents, who weigh others' welfare alongside their own, can close this gap and achieve outcomes that are socially superior and individually beneficial. Experimentally, we show that in multi-agent resource-allocation environments and canonical social dilemmas where agents are powered by large language models, prosociality is beneficial. The implication for AI safety is clear: to enable cooperative interactions at scale, designing adequate mechanisms is not sufficient; agents must be built to be intrinsically prosocial.
| Comments: | 42 pages |
| Subjects: | Computer Science and Game Theory (cs.GT); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08426 [cs.GT] |
| (or arXiv:2605.08426v1 [cs.GT] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08426 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xuanqiang 'Angelo' Huang [view email]
[v1]
Fri, 8 May 2026 19:37:07 UTC (3,121 KB)