EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems EICS003

Anton Wolter, Leon Haag, Vaishali Dhanoa, Niklas Elmqvist

Proceedings of the ACM on Human-Computer Interaction · 30.06.2026 · 10 (4) · 1-35

DOI: 10.1145/3812772 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Human-Computer Interaction, online erschienen am 29.06.2026. Verfasst von Anton Wolter und 3 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Villum Fonden.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Domain experts possess tacit knowledge that they cannot easily articulate through explicit specifications. When experts modify AI-generated artifacts by correcting terminology, restructuring arguments, and adjusting emphasis, these edits reveal domain understanding that remains latent in traditional prompt-based interactions. Current systems treat such modifications as endpoint corrections rather than as implicit specifications that could reshape subsequent reasoning. We propose context-mediated domain adaptation , a paradigm where user modifications to system-generated artifacts serve as implicit domain specification that reshapes Large Language Model (LLM)-powered multi-agent reasoning behavior. Through our system Seedentia , a web-based multi-agent framework for sense-making, we demonstrate bidirectional semantic links between generated artifacts and system reasoning. Our approach enables specification bootstrapping where vague initial prompts evolve into precise domain specifications through iterative human-AI collaboration, implicit knowledge transfer through reverse-engineered user edits, and in-context learning where agent behavior adapts based on observed correction patterns. We present results from an evaluation with domain experts who generated and modified research questions from academic papers. Our system extracted 46 domain knowledge entries from user modifications, demonstrating the feasibility of capturing implicit expertise through edit patterns, though the limited sample size constrains conclusions about systematic quality improvements.

Förderung

  • Villum Fonden

Zitieren

APA

Wolter, A., Haag, L., Dhanoa, V., & Elmqvist, N. (2026). Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems EICS003. Proceedings of the ACM on Human-Computer Interaction, 10(4), 1-35. https://doi.org/10.1145/3812772

Vancouver

Wolter A, Haag L, Dhanoa V, Elmqvist N. Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems EICS003. Proceedings of the ACM on Human-Computer Interaction. 2026;10(4):1-35. doi:10.1145/3812772

BibTeX
@article{Wolter2026,
  author = {Wolter, Anton and Haag, Leon and Dhanoa, Vaishali and Elmqvist, Niklas},
  title = {Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems EICS003},
  journal = {Proceedings of the ACM on Human-Computer Interaction},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {1--35},
  doi = {10.1145/3812772}
}
Kostenlos starten →