A knowledge-graph cognitive prototype plus beam-search self-refinement lets LLM agents simulate students' imperfect programming solutions more accurately than plain prompting.
The ability to code is a prerequisite of software development
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents
A knowledge-graph cognitive prototype plus beam-search self-refinement lets LLM agents simulate students' imperfect programming solutions more accurately than plain prompting.