Measuring Cognitive Engagement in Collaborative Discourse with an Extended ICAP Framework: Comparing Human Annotation, In-Context Learning, and Reflective LLM Agents

arXiv 2607.28651 ↗First posted 7 Jun 2026cs.HC cs.CL cs.CYcited by 0

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

Abstract (arXiv)

Collaboration supports learning and problem-solving, but its effectiveness depends on cognitive engagement during discourse. This study applies an extended 7-point ICAP framework based on the Interactive, Constructive, Active, and Passive modes to characterize variation in cognitive engagement during collaborative dialogue. Engagement was coded by trained human annotators and compared with large language model (LLM)-based labeling approaches, including in-context learning (ICL), zero-shot prompting, and self-reflective agents. Interrater reliability among human annotators was robust across framework refinement stages (kappa = 0.906-0.998), higher than the moderate agreement observed for ICL-based annotation (kappa = 0.541-0.609). The human-refined framework improved agreement among human annotators (Delta kappa = 0.10), but produced only modest gains for ICL-based LLMs (Delta kappa less than 0.04). Agent-refined frameworks improved cross-model agreement but remained below the human-refined framework. These findings highlight the promise of agent-based approaches and the importance of continued interaction between theory-guided human annotation and LLM-based methods in future work.

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 11 of its 37 references that are in the map. First posted on arXiv 7 Jun 2026.

Builds on

11 of 37 references.

Closest ancestors · 2

Same direction, newest first

Other references · 9

2020Language Models are Few-Shot Learnerscited by 32,419
2024GPT-4o System Cardcited by 4,588
2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
2025OpenAI GPT-5 System Cardcited by 989
2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
2024Large Language Models for Data Annotation and Synthesis: A Surveycited by 205
2024MEGAnno+: A Human-LLM Collaborative Annotation Systemcited by 47
2024Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuningcited by 21
2025Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Taskscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way