Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 10 of 10 for “"Multi-Agent Debate"”.
-
Calibrated Multi-Agent Debate for Explainable AI: Traceable Decision-Making Across Domains
… adoption in high-stakes settings. There are multiple domains in which AI requires explainability to ensure accountability, including cybersecurity, software testing, telecommunications, and regulatory compliance. There are emerging regulatory frameworks, such as the European Union Artificial …
-
Collective reasoning on multi-agent debates: A coherent approach
… and citizens, this dissertation explores multi-agent debates and collective reasoning. We present three novel approaches to represent a multi-agent debate —the Target oriented discussion framework, the Relational model and the Abstract multi-agent debate— and we use them to study …
-
Daugiaagentinių debatų įtaka lokalių didelių kalbos modelių (LLM) kodo generavimo efektyvumui skirtingo sudėtingumo užduotyse /
… structured code. This work studies whether multi-agent debate, where several models iteratively propose, critique and revise each other's solutions, can narrow this gap. A modular multi-agent debate system tailored to 7-9 billion parameter models was designed and implemented. The whole …
-
A Comparative Study of Inference-Time Scaling Strategies for Large Language Models
… across arithmetic and compositional tasks. Multi-agent debate with heterogeneous critic-solver pairs achieves the highest overall accuracy on object counting, surpassing PRM guidance. Majority voting provides reliable, compute-efficient improvements across most settings when answer diversity …
-
Toward Deliberative AI: Multi-Agent LLMs for Real-World Reasoning
Multi-agent debate has emerged as a promising strategy for improving the reasoning abilities of large language models (LLMs). However, existing approaches often fall short due to inefficiencies, shallow agreement, and a lack of real-world applicability. In this thesis, we introduce two novel …
-
Beyond the Visible: Transforming AR/VR Software Engineering Through Empirical Discovery, Metamorphic Testing, and Multi-Agent Intelligence
… evalua- tion framework showing that multi-agent debate improves the reliability of metamorphic relation identification, and then through a repository-aware generation framework that uses hierarchical code context and deliberative refinement to discover new AR-specific relations …
-
HASSUM : hierarchical agent system with semantic uncertainty metrics
Multi-Agent Systems (MASs) built on large language models (LLMs) have emerged as a promising framework for tackling complex, multi-step reasoning tasks through coordinated agent interactions. However, the additional complexity of these systems often increases unreliable outputs due to compounding …
-
Enabling Small Language Models as Efficient and Capable Agents
Most agentic systems today are built around large language models (LLMs) accessed through proprietary APIs (for example, GPT, Claude, and Gemini), which raises concerns about cost, latency, and privacy. This thesis argues that small language models (SLMs), typically under 30 billion parameters, can …
-
Použití multiagentního systému pro distribuovanou ochranu před kyberútoky
… řada článků, ve kterých jsou LLM používány v multi-agentních systémech pro řešení problémů a ve svých oblastech použití se osvědčují. Dosud však nebyl učiněn žádný pokus o použití multi-agentního systému založeného na LLM agentech v oblasti kybernetiky. Náš systém, nazvaný MAD-Shield, jsme …
-
Simulace lidské interakce s využitím AI
… pro simulaci konverzací více osob pomocí LLM agentů s daty o reálných lidech. Současně je představen nový přístup pro volbu pořadí řečí agentů nazvaný postupný rozhovor s potřebou agenta mluvit. Empirické studie prokazují výkonnost nástroje v mnoha scénářích hodnocení a překonávají porovnávaná …