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

arXiv: https://arxiv.org/abs/2603.24858 · HTML: https://mlsanity.com/paper/2603.24858/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 59 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review](https://mlsanity.com/paper/2504.19678/) (2025)
- [Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools](https://mlsanity.com/paper/2502.04644/) (2025)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [Interactive Debugging and Steering of Multi-Agent AI Systems](https://mlsanity.com/paper/2503.02068/) (2025)
- [Data Formulator: AI-powered Concept-driven Visualization Authoring](https://mlsanity.com/paper/2309.10094/) (2023)
- [PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling](https://mlsanity.com/paper/2402.08702/) (2024)
- [The ART of LLM Refinement: Ask, Refine, and Trust](https://mlsanity.com/paper/2311.07961/) (2023)
- [AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making](https://mlsanity.com/paper/2312.04494/) (2023)
- [InsightLens: Augmenting LLM-Powered Data Analysis with Interactive Insight Management and Navigation](https://mlsanity.com/paper/2404.01644/) (2024)
- [KG4Vis: A Knowledge Graph-Based Approach for Visualization Recommendation](https://mlsanity.com/paper/2107.12548/) (2021)
- [Snowy: Recommending Utterances for Conversational Visual Analysis](https://mlsanity.com/paper/2110.04323/) (2021)
- [DataSite: Proactive Visual Data Exploration with Computation of Insight-based Recommendations](https://mlsanity.com/paper/1802.08621/) (2018)
- [Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems](https://mlsanity.com/paper/2505.19101/) (2025)
- [Exploring Prompt Engineering Practices in the Enterprise](https://mlsanity.com/paper/2403.08950/) (2024)
- [Self-Taught Agentic Long Context Understanding](https://mlsanity.com/paper/2502.15920/) (2025)
- [Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunities](https://mlsanity.com/paper/2304.01311/) (2023)
- [Charts-of-Thought: Enhancing LLM Visualization Literacy Through Structured Data Extraction](https://mlsanity.com/paper/2508.04842/) (2025)
- [Multi-Agent Data Visualization and Narrative Generation](https://mlsanity.com/paper/2509.00481/) (2025)
- [Deep Reinforcement Learning with Explicit Context Representation](https://mlsanity.com/paper/2310.09924/) (2023)
- [LLM Augmentations to support Analytical Reasoning over Multiple Documents](https://mlsanity.com/paper/2411.16116/) (2024)
- [A Composable Agentic System for Automated Visual Data Reporting](https://mlsanity.com/paper/2509.05721/) (2025)
- [Generalization of Agent Behavior through Explicit Representation of Context](https://mlsanity.com/paper/2006.11305/) (2020)
- [Representing Real-Time Multi-User Collaboration in Visualizations](https://mlsanity.com/paper/2009.02587/) (2020)
- [Tell Me Without Telling Me: Two-Way Prediction of Visualization Literacy and Visual Attention](https://mlsanity.com/paper/2508.03713/) (2025)

## Abstract (arXiv)

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.