{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/2091"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/2091","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Adaptive self-prompting in agentic LLM frameworks for embedded code fault detection","abstract":"This thesis investigates adaptive self-prompting in agentic large language model (LLM) frameworks for code fault detection in embedded systems. Traditional static analysis and existing LLM-based approaches often rely on fixed prompts and exhibit overconfidence, leading to misclassifications. To address these limitations, we propose two complementary frameworks: Agentic Retrieval-Augmented Generation (A-RAG) and Agentic Supervised Fine-Tuning (A-SFT), along with a hybrid architecture integrating both. A-RAG employs confidence-triggered adaptive retrieval on a curated vector knowledge base of coding standards, while A-SFT leverages self-evaluation and instruction adaptation to refine the model’s reasoning during training. The frameworks are evaluated on a unified dataset combining the Toyota ITC benchmark and a subset of Big-Vul. Experimental results demonstrate that adaptive self-prompting improves overall F1-score by 6.7-18% over static baselines and reduces high-confidence misclassifications by 6.1-17.6%. Pairwise improvements are statistically significant under Bonferroni-corrected McNemar tests, indicating enhanced safety for embedded C code analysis.","abstract_html":"This thesis investigates adaptive self-prompting in agentic large language model (LLM) frameworks for code fault detection in embedded systems. Traditional static analysis and existing LLM-based approaches often rely on fixed prompts and exhibit overconfidence, leading to misclassifications. To address these limitations, we propose two complementary frameworks: Agentic Retrieval-Augmented Generation (A-RAG) and Agentic Supervised Fine-Tuning (A-SFT), along with a hybrid architecture integrating both. A-RAG employs confidence-triggered adaptive retrieval on a curated vector knowledge base of coding standards, while A-SFT leverages self-evaluation and instruction adaptation to refine the model’s reasoning during training. The frameworks are evaluated on a unified dataset combining the Toyota ITC benchmark and a subset of Big-Vul. Experimental results demonstrate that adaptive self-prompting improves overall F1-score by 6.7-18% over static baselines and reduces high-confidence misclassifications by 6.1-17.6%. Pairwise improvements are statistically significant under Bonferroni-corrected McNemar tests, indicating enhanced safety for embedded C code analysis.","abstract_has_math":false,"creators":["Muhtadi, Maher"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Applied Science (MASc)","degree_level":null,"degree_discipline":"Software Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Mahmoud, Qusay H.","Azim, Akramul"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-04-01","date_published":"2026-04-01","updated_at":"2026-07-24T05:35:20Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/2091","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mahmoud, Qusay H.","Azim, Akramul"]},{"key":"dc:creator","label":"Author","values":["Muhtadi, Maher"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-04-28T18:27:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-04-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Software Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Applied Science (MASc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/2091"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis investigates adaptive self-prompting in agentic large language model (LLM) frameworks for code fault detection in embedded systems. Traditional static analysis and existing LLM-based approaches often rely on fixed prompts and exhibit overconfidence, leading to misclassifications. To address these limitations, we propose two complementary frameworks: Agentic Retrieval-Augmented Generation (A-RAG) and Agentic Supervised Fine-Tuning (A-SFT), along with a hybrid architecture integrating both. A-RAG employs confidence-triggered adaptive retrieval on a curated vector knowledge base of coding standards, while A-SFT leverages self-evaluation and instruction adaptation to refine the model’s reasoning during training. The frameworks are evaluated on a unified dataset combining the Toyota ITC benchmark and a subset of Big-Vul. Experimental results demonstrate that adaptive self-prompting improves overall F1-score by 6.7-18% over static baselines and reduces high-confidence misclassifications by 6.1-17.6%. Pairwise improvements are statistically significant under Bonferroni-corrected McNemar tests, indicating enhanced safety for embedded C code analysis."]},{"key":"dc:title","label":"Title","values":["Adaptive self-prompting in agentic LLM frameworks for embedded code fault detection"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mahmoud, Qusay H.","Azim, Akramul"],"dc:creator":["Muhtadi, Maher"],"dc:date.accessioned":["2026-04-28T18:27:22Z"],"dc:date.issued":["2026-04-01"],"dc:description.abstract":["This thesis investigates adaptive self-prompting in agentic large language model (LLM) frameworks for code fault detection in embedded systems. Traditional static analysis and existing LLM-based approaches often rely on fixed prompts and exhibit overconfidence, leading to misclassifications. To address these limitations, we propose two complementary frameworks: Agentic Retrieval-Augmented Generation (A-RAG) and Agentic Supervised Fine-Tuning (A-SFT), along with a hybrid architecture integrating both. A-RAG employs confidence-triggered adaptive retrieval on a curated vector knowledge base of coding standards, while A-SFT leverages self-evaluation and instruction adaptation to refine the model’s reasoning during training. The frameworks are evaluated on a unified dataset combining the Toyota ITC benchmark and a subset of Big-Vul. Experimental results demonstrate that adaptive self-prompting improves overall F1-score by 6.7-18% over static baselines and reduces high-confidence misclassifications by 6.1-17.6%. Pairwise improvements are statistically significant under Bonferroni-corrected McNemar tests, indicating enhanced safety for embedded C code analysis."],"dc:identifier.uri":["https://hdl.handle.net/10155/2091"],"dc:language.iso":["en"],"dc:title":["Adaptive self-prompting in agentic LLM frameworks for embedded code fault detection"],"dc:type":["Thesis"],"thesis:degree_discipline":["Software Engineering"],"thesis:degree_name":["Master of Applied Science (MASc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:20Z"}