{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-5048"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-5048","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Trustworthy Intelligence Fusion for Search and Rescue: Designing Grounded and Secure Multi-Agent AI for Mission Decision Support","abstract":"Search and rescue (SAR) operations require teams to integrate uncertain information under severe time pressure. Large language model (LLM)-based multi-agent systems (MAS) can support decision-making, but they also risk producing hallucinated outputs and processing unreliable or malicious data. This thesis addresses these risks through three linked studies. First, it proposes a modular eight-agent SAR MAS architecture that reflects the structure of real SAR missions by assigning specialized roles to different agents. Second, it introduces a post-hoc probabilistic verification framework that checks LLM agent outputs against a probabilistic knowledge graph built from historical SAR incidents. Third, the thesis examines indirect adversarial threats, including prompt injection, knowledge-base poisoning, and adversarial examples, and evaluates corresponding lightweight defences. The results show that modular specialization, probabilistic grounding, and adversarial defences can improve the reliability and robustness of SAR decision support. The thesis contributes a prototype, evaluation method, and deployment guidance for safety-critical agentic AI.","abstract_html":"Search and rescue (SAR) operations require teams to integrate uncertain information under severe time pressure. Large language model (LLM)-based multi-agent systems (MAS) can support decision-making, but they also risk producing hallucinated outputs and processing unreliable or malicious data. This thesis addresses these risks through three linked studies. First, it proposes a modular eight-agent SAR MAS architecture that reflects the structure of real SAR missions by assigning specialized roles to different agents. Second, it introduces a post-hoc probabilistic verification framework that checks LLM agent outputs against a probabilistic knowledge graph built from historical SAR incidents. Third, the thesis examines indirect adversarial threats, including prompt injection, knowledge-base poisoning, and adversarial examples, and evaluates corresponding lightweight defences. The results show that modular specialization, probabilistic grounding, and adversarial defences can improve the reliability and robustness of SAR decision support. The thesis contributes a prototype, evaluation method, and deployment guidance for safety-critical agentic AI.","abstract_has_math":false,"creators":["Tan, Yayun"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Franz Kurfess","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:58Z","subjects":["Search and rescue","multi-agent systems","large language models","trustworthy AI","post-hoc verification","adversarial security","Other Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3343","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3343","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-5048","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Franz Kurfess","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Tan, Yayun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-06-12T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Search and rescue","multi-agent systems","large language models","trustworthy AI","post-hoc verification","adversarial security","Other Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3343"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Search and rescue (SAR) operations require teams to integrate uncertain information under severe time pressure. Large language model (LLM)-based multi-agent systems (MAS) can support decision-making, but they also risk producing hallucinated outputs and processing unreliable or malicious data. This thesis addresses these risks through three linked studies. First, it proposes a modular eight-agent SAR MAS architecture that reflects the structure of real SAR missions by assigning specialized roles to different agents. Second, it introduces a post-hoc probabilistic verification framework that checks LLM agent outputs against a probabilistic knowledge graph built from historical SAR incidents. Third, the thesis examines indirect adversarial threats, including prompt injection, knowledge-base poisoning, and adversarial examples, and evaluates corresponding lightweight defences. The results show that modular specialization, probabilistic grounding, and adversarial defences can improve the reliability and robustness of SAR decision support. The thesis contributes a prototype, evaluation method, and deployment guidance for safety-critical agentic AI."]},{"key":"dc:title","label":"Title","values":["Trustworthy Intelligence Fusion for Search and Rescue: Designing Grounded and Secure Multi-Agent AI for Mission Decision Support"]}]}],"canonical_facts":{"dc:contributor":["Franz Kurfess","Computer Science","College of Engineering"],"dc:creator":["Tan, Yayun"],"dc:date.available":["2026-06-12T07:00:00Z"],"dc:date.created":["2026-06-01T07:00:00Z"],"dc:description.abstract":["Search and rescue (SAR) operations require teams to integrate uncertain information under severe time pressure. Large language model (LLM)-based multi-agent systems (MAS) can support decision-making, but they also risk producing hallucinated outputs and processing unreliable or malicious data. This thesis addresses these risks through three linked studies. First, it proposes a modular eight-agent SAR MAS architecture that reflects the structure of real SAR missions by assigning specialized roles to different agents. Second, it introduces a post-hoc probabilistic verification framework that checks LLM agent outputs against a probabilistic knowledge graph built from historical SAR incidents. Third, the thesis examines indirect adversarial threats, including prompt injection, knowledge-base poisoning, and adversarial examples, and evaluates corresponding lightweight defences. The results show that modular specialization, probabilistic grounding, and adversarial defences can improve the reliability and robustness of SAR decision support. The thesis contributes a prototype, evaluation method, and deployment guidance for safety-critical agentic AI."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3343"],"dc:subject":["Search and rescue","multi-agent systems","large language models","trustworthy AI","post-hoc verification","adversarial security","Other Computer Engineering"],"dc:title":["Trustworthy Intelligence Fusion for Search and Rescue: Designing Grounded and Secure Multi-Agent AI for Mission Decision Support"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:58Z"}