Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems

TL;DR

This paper introduces context-mediated domain adaptation for multi-agent AI systems, leveraging user edits as implicit domain knowledge to improve reasoning and collaboration.

Contribution

It presents a novel paradigm where user modifications serve as implicit specifications, enabling adaptive reasoning in multi-agent systems through iterative human-AI interaction.

Findings

Extracted 46 domain knowledge entries from user edits

Demonstrated bidirectional semantic links between artifacts and reasoning

Showed feasibility of capturing implicit expertise via edit patterns

Abstract

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 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.