Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Tiny Data, Big Policy? Generative AI Agents for Context-Sensitive Climate Governance
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0001-8235-1637
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0001-6158-3543
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0002-6756-0147
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0003-4029-6574
2026 (English)In: Proceedings - 2026 IEEE 50th Annual Computers, Software, and Applications Conference, COMPSAC 2026 / [ed] Hossain Shahriar, Kazi Shafiul Alam, Hiroyuki Ohsaki, Stelvio Cimato, Miriam Capretz, Shamem Ahmed, Sheikh Iqbal Ahamed, AKM Jahangir Alam Majumder, Munirul Haque, Tomoki Yoshihisa, Alfredo Cuzzocrea, Michiharu Takemoto, Nazmus Sakib, Marwa Elsayed, Institute of Electrical and Electronics Engineers Inc. , 2026, p. 1165-1174Conference paper, Published paper (Refereed)
Abstract [en]

The climate crisis is becoming a pressing concern for humanity, and policymakers face the challenge of collecting and processing information to formulate context-sensitive policies to mitigate its impact. This study explores the potential of generative agents in developing context-specific climate policies using minimal but strategically relevant data inputs. It considers key environmental indicators as input for five countries: Brazil, China, Germany, India, and the United States. Findings reveal recurring policy themes across countries, such as the necessity of renewable energy expansion and community engagement. Additionally, this study demonstrates the ability of AI-driven approaches to generate actionable policy recommendations tailored to a country's socio-economic and political context. This study further examines the alignment of AI-generated policies with official Nationally Determined Contributions using semantic similarity analysis and also examines the marginal contribution of individual agents through an ablation study. Overall, in the context of the AI-based climate literature, this study shifts the focus from predictive analysis to actionable decision-making and contributes to the growing discourse on the role of generative agents in climate governance by developing context-sensitive climate policies through a multi-agent framework relying on minimal data inputs.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2026. p. 1165-1174
Keywords [en]
Generative Agents, Climate Policy, Minimal data
National Category
Climate Science Energy Systems
Research subject
Machine Learning
Identifiers
URN: urn:nbn:se:ltu:diva-120008DOI: 10.1109/COMPSAC69091.2026.00158Scopus ID: 2-s2.0-105048923297OAI: oai:DiVA.org:ltu-120008DiVA, id: diva2:2108824
Conference
IEEE Annual International Conference on Computers, Software, and Applications Conference (COMPSAC 2026), Madrid, Spain, July 7-10, 2026
Funder
Knut and Alice Wallenberg FoundationEuropean Regional Development Fund (ERDF), MARTINA
Note

ISBN for host publication: 979-8-3315-4497-3

Available from: 2026-10-07 Created: 2026-10-07 Last updated: 2026-10-07Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopusConference program

Authority records

Khatua, AparupMokayed, HamamLiwicki, FoteiniLiwicki, Marcus

Search in DiVA

By author/editor
Khatua, AparupMokayed, HamamLiwicki, FoteiniLiwicki, Marcus
By organisation
Embedded Internet Systems Lab
Climate ScienceEnergy Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 6 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf