mlsanityData to 14 Oct 2026

Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems

arXiv 2603.24858 ↗First posted 25 Mar 2026cs.HC cs.MAcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

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.

Builds on

32 of 59 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review28 Apr
  2. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools7 Feb
  3. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Tasks4 Jun

Other references · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  3. 2023Teaching Large Language Models to Self-Debugcited by 988
  4. 2023Explainability for Large Language Models: A Surveycited by 333
  5. 2023ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testingcited by 88
  6. 2024Aligning LLM Agents by Learning Latent Preference from User Editscited by 69
  7. 2025Interactive Debugging and Steering of Multi-Agent AI Systemscited by 68
  8. 2023Data Formulator: AI-powered Concept-driven Visualization Authoringcited by 32
  9. 2024PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Samplingcited by 32
  10. 2023The ART of LLM Refinement: Ask, Refine, and Trustcited by 29
  11. 2023AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Makingcited by 21
  12. 2024InsightLens: Augmenting LLM-Powered Data Analysis with Interactive Insight Management and Navigationcited by 18
17 more
  1. 2021KG4Vis: A Knowledge Graph-Based Approach for Visualization Recommendationcited by 17
  2. 2021Snowy: Recommending Utterances for Conversational Visual Analysiscited by 14
  3. 2018DataSite: Proactive Visual Data Exploration with Computation of Insight-based Recommendationscited by 12
  4. 2025Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systemscited by 12
  5. 2024Exploring Prompt Engineering Practices in the Enterprisecited by 11
  6. 2025Self-Taught Agentic Long Context Understandingcited by 10
  7. 2023Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunitiescited by 9
  8. 2025Charts-of-Thought: Enhancing LLM Visualization Literacy Through Structured Data Extractioncited by 6
  9. 2025Multi-Agent Data Visualization and Narrative Generationcited by 4
  10. 2023Deep Reinforcement Learning with Explicit Context Representationcited by 3
  11. 2024LLM Augmentations to support Analytical Reasoning over Multiple Documentscited by 3
  12. 2025A Composable Agentic System for Automated Visual Data Reportingcited by 3
  13. 2020Generalization of Agent Behavior through Explicit Representation of Contextcited by 2
  14. 2020Representing Real-Time Multi-User Collaboration in Visualizationscited by 1
  15. 2025Tell Me Without Telling Me: Two-Way Prediction of Visualization Literacy and Visual Attentioncited by 1
  16. 2025DRIVE-T: A Methodology for Discriminative and Representative Data Viz Item Selection for Literacy Construct and Assessmentcited by 1
  17. 2025Participatory AI: A Scandinavian Approach to Human-Centered AIcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
  2. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experience
  3. 2025Agent Fine-tuning through Distillation for Domain-specific LLMs in Microdomains
  4. 2025Experience-Guided Adaptation of Inference-Time Reasoning Strategies
  5. 2025Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support
  6. 2026Nurture-First Agent Development: Building Domain-Expert AI Agents Through Conversational Knowledge Crystallization
  7. 2025Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
  8. 2026Self-Adapting Group of Experts for Multi-Agent Reasoning