{"690326":{"#nid":"690326","#data":{"type":"event","title":"PhD Proposal by Kamel Alrashedy","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E:\u0026nbsp;Feedback-Guided LLM Reasoning: A Unified Closed-Loop Framework for Code Generation and Decision Making\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate\u003C\/strong\u003E: Tuesday, May 19, 2026\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E: 2:30 PM to 4:30 PM Eastern Time (US)\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E:\u0026nbsp;Klaus 1315\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EVirtual Meeting\u003C\/strong\u003E:\u0026nbsp;\u003Ca href=\u0022https:\/\/nam12.safelinks.protection.outlook.com\/?url=https%3A%2F%2Fgatech.zoom.us%2Fj%2F91561524771\u0026amp;data=05%7C02%7Ctm186%40gtvault.onmicrosoft.com%7Ccc85edbee7b74848fe9308deb13dedc8%7C482198bbae7b4b258b7a6d7f32faa083%7C1%7C0%7C639143076803904512%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C\u0026amp;sdata=DlY19lIDgjL516LCIfxxO7jDboay%2FcfoP6yCmXg60Pk%3D\u0026amp;reserved=0\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/91561524771\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EKamel Alrashedy\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ECS Ph.D. Student\u003C\/p\u003E\u003Cp\u003ESchool of Interactive Computing\u003C\/p\u003E\u003Cp\u003ECollege of Computing\u003C\/p\u003E\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/nam12.safelinks.protection.outlook.com\/?url=https%3A%2F%2Fkamel773.github.io%2F\u0026amp;data=05%7C02%7Ctm186%40gtvault.onmicrosoft.com%7Ccc85edbee7b74848fe9308deb13dedc8%7C482198bbae7b4b258b7a6d7f32faa083%7C1%7C0%7C639143076803974869%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C\u0026amp;sdata=k%2BZBW9rHflppo%2F6nPc5tGKZVwTrRtmYCl0gQIN02yTE%3D\u0026amp;reserved=0\u0022\u003Ehttps:\/\/kamel773.github.io\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Matthew Gombolay\u0026nbsp;- Advisor, School of Interactive Computing\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Kartik Goyal\u0026nbsp;- Georgia Tech, School of Interactive Computing\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Zsolt Kira\u0026nbsp;- Georgia Tech, School of Interactive Computing\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Shreyes Melkote\u0026nbsp;- Georgia Tech,\u0026nbsp;School of Mechanical Engineering\u003C\/p\u003E\u003Cp\u003EDr. Jesse Thomason - University of Southern California, Department of Computer Science\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003ELarge Language Models (LLMs) have shown strong potential for improving productivity in software engineering, design, and decision support. However, when deployed in real-world tasks, they often struggle to produce outputs that are correct, secure, and compliant with constraints. This thesis develops Feedback-Guided LLM Reasoning (FGLR), a closed-loop interaction framework that enables language models to improve solution quality through iterative feedback from external tools, rather than relying solely on static prompting or internal model knowledge. First, I introduce CADCodeVerify, a feedback-driven framework for CAD code generation that uses vision-language verification to iteratively detect and correct structural and geometric errors. Second, I develop Feedback-Driven Security Patching (FDSP), which integrates static code analyzers with LLMs to identify vulnerabilities and iteratively refine insecure code. Third, I propose Constraints-of-Thought (Const-o-T), a structured reasoning framework that transforms natural language strategies into executable intent-constraint representations, enabling constraint-guided planning and search. Finally, I investigate reliable feedback as a fundamental challenge in feedback-driven reasoning, studying when iterative refinement improves or degrades\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EFeedback-Guided LLM Reasoning: A Unified Closed-Loop Framework for Code Generation and Decision Making\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Feedback-Guided LLM Reasoning: A Unified Closed-Loop Framework for Code Generation and Decision Making"}],"uid":"27707","created_gmt":"2026-05-18 15:38:28","changed_gmt":"2026-05-18 15:39:00","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-05-19T14:30:00-04:00","event_time_end":"2026-05-19T16:30:00-04:00","event_time_end_last":"2026-05-19T16:30:00-04:00","gmt_time_start":"2026-05-19 18:30:00","gmt_time_end":"2026-05-19 20:30:00","gmt_time_end_last":"2026-05-19 20:30:00","rrule":null,"timezone":"America\/New_York"},"location":"Klaus 1315","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}