EUVIMEDEUVIMED entdecken
Crossref

Strategic Tool Enhanced AI Agent for Multi-Issue Negotiation (Student Abstract)

Daiki Kitashima, Ryota Higa, Katsuhide Fujita

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41246-41248

DOI: 10.1609/aaai.v40i48.42230 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Daiki Kitashima und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated negotiation, a form of interaction among autonomous agents, plays a central role in multi-agent systems, yet the application of large language model (LLM) in this domain remains underexplored. An LLM can serve as a meta-strategist, adaptively selecting explicit strategies for execution by external strategic tools based on its capabilities. We propose a negotiation AI agent equipped with explicit strategic tools, including time-dependent and tit-for-tat negotiation strategies. Our results show that strategic tool enhanced negotiators achieve approximately 16% higher average utility compared with baseline, latest LLM negotiators.

Zitieren

APA

Kitashima, D., Higa, R., & Fujita, K. (2026). Strategic Tool Enhanced AI Agent for Multi-Issue Negotiation (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41246-41248. https://doi.org/10.1609/aaai.v40i48.42230

Vancouver

Kitashima D, Higa R, Fujita K. Strategic Tool Enhanced AI Agent for Multi-Issue Negotiation (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41246-41248. doi:10.1609/aaai.v40i48.42230

BibTeX
@article{Kitashima2026,
  author = {Kitashima, Daiki and Higa, Ryota and Fujita, Katsuhide},
  title = {Strategic Tool Enhanced AI Agent for Multi-Issue Negotiation (Student Abstract)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41246--41248},
  doi = {10.1609/aaai.v40i48.42230}
}
Kostenlos starten →