paper-with-me

Papers

ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning

2026-06-11 · Fuqiang Niu, Bowen Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.13197

Code (0)

등록된 구현이 없습니다.

Tasks

Outlier Detection

Similar Papers 제목 키워드 기반

ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors

2026-07-16 · Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho, Pai Chet Ng 외 arxiv

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

2025-07-21 · Tianneng Shi, Kaijie Zhu, Zhun Wang, Yuqi Jia 외 arxiv

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

2026-02-12 · Carl Qi, Xiaojie Wang, Silong Yong, Stephen Sheng 외 arxiv

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

2026-05-08 · Ye Liu, Botao Yu, Xinyi Ling, Daniel Adu-Ampratwum 외 arxiv

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

2026-01-26 · Gabriel Lee Jun Rong, Christos Korgialas, Dion Jia Xu Ho, Pai Chet Ng 외 arxiv

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…