"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussions
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
Asynchronous online discussions enable diverse participants to co-construct knowledge beyond individual contributions. This process ideally evolves through sequential phases, from superficial information exchange to deeper synthesis. However, many discussions stagnate in the early stages. Existing AI interventions typically target isolated phases, lacking mechanisms to progressively advance knowledge co-construction, and the impacts of different intervention styles in this context remain unclear and warrant investigation. To address these gaps, we conducted a design workshop to explore AI intervention strategies (task-oriented and/or relationship-oriented) throughout the knowledge co-construction process, and implemented them in an LLM-powered agent capable of facilitating progression while consolidating foundations at each phase. A within-subject study (N=60) involving five consecutive asynchronous discussions showed that the agent consistently promoted deeper knowledge progression, with different styles exerting distinct effects on both content and experience. These findings provide actionable guidance for designing adaptive AI agents that sustain more constructive online discussions.
Key facts. Cited by 1 paper in the map (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 18 of its 166 references that are in the map. First posted on arXiv 27 Sep 2025.
Builds on
18 of 166 references.
References · 18
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2022Survey of Hallucination in Natural Language Generationcited by 2,075
- 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 139
- 2023Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Makingcited by 67
- 2019How should my chatbot interact? A survey on human-chatbot interaction designcited by 56
- 2023RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressionscited by 43
- 2024Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Makingcited by 38
- 2024"Are You Really Sure?" Understanding the Effects of Human Self-Confidence Calibration in AI-Assisted Decision Makingcited by 26
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Explorationcited by 10
- 2022The Effects of System Initiative during Conversational Collaborative Searchcited by 9
- 2025DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decompositioncited by 9
- 2023Engaged and Affective Virtual Agents: Their Impact on Social Presence, Trustworthiness, and Decision-Making in the Group Discussioncited by 7
6 more
- 2024Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generationcited by 7
- 2025CoKnowledge: Supporting Assimilation of Time-synced Collective Knowledge in Online Science Videoscited by 4
- 2025Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferencescited by 3
- 2023Engage Wider Audience or Facilitate Quality Answers? a Mixed-methods Analysis of Questioning Strategies for Research Sensemaking on a Community Q&A Sitecited by 2
- 2022When Gamification Spoils Your Learning: A Qualitative Case Study of Gamification Misuse in a Language-Learning Appcited by 1
- 2024Sharing Frissons among Online Video Viewers: Exploring the Design of Affective Communication for Aesthetic Chillscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent
- 2025Agentic AI as Undercover Teammates: Argumentative Knowledge Construction in Hybrid Human-AI Collaborative Learning
- 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
- 2025Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation
- 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration
- 2025SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal Reasoning
- 2026Nurture-First Agent Development: Building Domain-Expert AI Agents Through Conversational Knowledge Crystallization
- 2024Conversational Agents as Catalysts for Critical Thinking: Challenging Design Fixation in Group Design