Papers with end-to-end tutoring workflow
IntelliCode: A Multi-Agent LLM Tutoring System with Centralized Learner Modeling (2026.eacl-demo)
Copied to clipboard
| Challenge: | Existing LLM tutors lack persistent representations of learner knowledge . current systems provide inconsistent hints, overlook dependencies between concepts . |
| Approach: | They propose a multi-agent LLM tutoring system that integrates mastery estimates, misconceptions, review schedules, and engagement signals. |
| Outcome: | The proposed system integrates skill assessment, learner profiling, graduated hinting, curriculum selection, spaced repetition, and engagement monitoring over a shared state under a single-writer policy. |