{"paper":{"title":"Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"KITE uses retrieval from course materials and Socratic scaffolding to help simulated students give more accurate answers on algorithm tracing and procedural tasks.","cross_cats":["cs.CY","cs.IR"],"primary_cat":"cs.AI","authors_text":"Arto Hellas, Aum Pandya, Bita Akram, Griffin Pitts, Juho Leinonen, Mragisha Jain, Narges Norouzi, Peter Brusilovsky, Tirth Bhatt","submitted_at":"2026-05-13T04:37:45Z","abstract_excerpt":"Students learning algorithms often need support as they interpret traces, debug reasoning errors, and apply procedures across unfamiliar problem instances. In this paper, we present KITE (Knowledge-Informed Tutoring Engine), a Retrieval-Augmented Generation (RAG)-based intelligent tutoring system designed to serve as a classroom teaching assistant for algorithmic reasoning and problem-solving tasks. KITE uses an intent-aware Socratic response strategy to tailor support to different student needs, responding with targeted hints, guiding questions, and progressive scaffolding intended to strengt"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"using simulated students, KITE's feedback helped the student models produce more accurate follow-up responses on procedural and tracing questions, suggesting that its scaffolding can support algorithmic problem-solving.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The two-turn simulated student pipeline with a weaker language model accurately reflects how real human students would interpret and benefit from the tutoring feedback.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"KITE is a RAG-based tutoring system delivering intent-aware Socratic feedback from course content that improves accuracy of simulated student responses on algorithm tracing and procedural questions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"KITE uses retrieval from course materials and Socratic scaffolding to help simulated students give more accurate answers on algorithm tracing and procedural tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9c6f744a7eed41685f49cd794979d7804a9aef79d40679f39dcbf56704a22661"},"source":{"id":"2605.12988","kind":"arxiv","version":1},"verdict":{"id":"e5c002e2-1398-47e9-999d-88ad0fb2f0ad","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:49:39.555028Z","strongest_claim":"using simulated students, KITE's feedback helped the student models produce more accurate follow-up responses on procedural and tracing questions, suggesting that its scaffolding can support algorithmic problem-solving.","one_line_summary":"KITE is a RAG-based tutoring system delivering intent-aware Socratic feedback from course content that improves accuracy of simulated student responses on algorithm tracing and procedural questions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The two-turn simulated student pipeline with a weaker language model accurately reflects how real human students would interpret and benefit from the tutoring feedback.","pith_extraction_headline":"KITE uses retrieval from course materials and Socratic scaffolding to help simulated students give more accurate answers on algorithm tracing and procedural tasks."},"references":{"count":33,"sample":[{"doi":"","year":2025,"title":"Ceur Workshop Proceedings , volume=","work_id":"6a8f43e6-07eb-4aaf-851a-7d2299193e47","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2007,"title":"Educational psychology review , volume=","work_id":"26ededde-c048-4a52-a7bf-1f528ebe437b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+ NLP) , pages=","work_id":"3e556444-e94c-42a9-8784-c769c7eab290","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Trust and Reliance on AI in Education: AI Literacy and Need for Cognition as Moderators","work_id":"9b4079ba-1e79-4448-abb0-fa9e4fd4bcf3","ref_index":4,"cited_arxiv_id":"2604.01114","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2602.20547 (2026)","work_id":"338bfb54-cd07-4ebe-92ab-a38f489fdb89","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"c23f8668e7597b621e1ece73c703b81e1fddcf3bd182b88b4d234fde0851f987","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}