ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning
Multi-agent debate (MAD) can improve large language model reasoning, but fixed debate pipelines often waste computation and can amplify correlated errors among similar agents. We propose ARMOR-MAD, a training-free heterogeneous MAD framework that treats debate as conditional computation. ARMOR-MAD combines three components: Pre-debate Agreement Routing (PAR) decides whether independently generated Round-0 answers require debate; Early Agreement Stopping Evaluator (EASE) stops debate after convergence; and Semantic Outlier Detection (SOD) down-weights abnormal final answers during aggregation. Across MATH Level 5, GSM8K, MMLU, and MMLU-Pro, ARMOR-MAD consistently improves over fixed-round heterogeneous debate with the same model pool, reaching 65.5\%, 96.5\%, 90.0\%, and 81.5\% accuracy, respectively. The results suggest that genuine model heterogeneity and agreement-based control are both important for making MAD more accurate and efficient.
Code (0)
등록된 구현이 없습니다.
Tasks
Outlier DetectionSimilar Papers 제목 키워드 기반
ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic a…
PromptArmor: Simple yet Effective Prompt Injection Defenses
Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specifi…
Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning
Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or assume access to ample human annotation…
ARMOR: An Agentic Framework for Reaction Feasibility Prediction via Adaptive Utility-aware Multi-tool Reasoning
Reaction feasibility prediction, as a fundamental problem in computational chemistry, has benefited from diverse tools enabled by recent advances in artificial intelligence, particularly large language models. However, t…
ARMOR: Agentic Reasoning for Methods Orchestration and Reparameterization for Robust Adversarial Attacks
Existing automated attack suites operate as static ensembles with fixed sequences, lacking strategic adaptation and semantic awareness. This paper introduces the Agentic Reasoning for Methods Orchestration and Reparamete…