arXiv:2601.04387v2 Announce Type: replace Abstract: Negotiation is a core component of social intelligence, requiring agents to balance strategic reasoning, cooperation, and social norms. Recent work shows that LLMs can engage in multi-turn negotiation, yet nearly all evaluations occur exclusively in English. Using controlled multi-agent simulations across Ultimatum, Buy-Sell, and Resource Exchange games, we systematically isolate language effects across English and four Indic framings (Hindi, Punjabi, Gujarati, Marwadi) by holding game rules, model parameters, and incentives constant across a
The rapid advancement of LLMs has brought their negotiation capabilities to the forefront, making the nuances of linguistic and cultural effects a critical area of study for real-world deployment.
This research reveals how linguistic and cultural biases inherent in LLMs, especially those trained predominantly on English, can significantly influence outcomes in critical negotiation scenarios.
Our understanding of LLM capabilities in complex social interactions is refined by highlighting the critical role of language and cultural framing, moving beyond simplistic English-centric evaluations.
- · AI ethicists and policy makers
- · Developers of multilingual LLMs
- · Companies operating in diverse linguistic markets
- · Monolingual LLM developers
- · Organizations relying on undifferentiated LLM applications for global negotiatio
Further research and development into culturally and linguistically nuanced LLMs will accelerate.
AI deployment in international diplomacy, commerce, and complex social interactions will be re-evaluated with a focus on linguistic inclusivity and bias mitigation.
The development of 'cultural intelligence' benchmarks for AI could become a critical standard for advanced AI systems.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI