Imagen de Portada

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Wei, Li, Shixuan, Ping, Heng, Zhang, Peiyu, Bogdan, Paul, Thomason, Jesse
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs
por: Yang, Wei, et al.
Publicado: (2025)

VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation
por: Ping, Heng, et al.
Publicado: (2025)

COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation
por: Ping, Heng, et al.
Publicado: (2026)

POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
por: Ping, Heng, et al.
Publicado: (2026)

HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL
por: Ping, Heng, et al.
Publicado: (2025)

ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models
por: Li, Shixuan, et al.
Publicado: (2025)

Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning
por: Yang, Wei, et al.
Publicado: (2025)

Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM
por: Hu, Zizhao, et al.
Publicado: (2026)

Why Do Some Inputs Break Low-Bit LLM Quantization?
por: Chang, Ting-Yun, et al.
Publicado: (2025)

EMS: Multi-Agent Voting via Efficient Majority-then-Stopping
por: Liu, Yiqing, et al.
Publicado: (2026)

Counterfactual Trace Auditing of LLM Agent Skills
por: Zhou, Xiaolin, et al.
Publicado: (2026)

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
por: Hu, Tianyu, et al.
Publicado: (2025)

CollabEval: Enhancing LLM-as-a-Judge via Multi-Agent Collaboration
por: Qian, Yiyue, et al.
Publicado: (2026)

Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering
por: Zhao, Zixiao, et al.
Publicado: (2026)

Towards Security-Auditable LLM Agents: A Unified Graph Representation
por: Li, Chaofan, et al.
Publicado: (2026)

Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent
por: Haji, Fatemeh, et al.
Publicado: (2024)

Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting
por: Zhang, Chaoyuan, et al.
Publicado: (2025)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
por: Limozin, Alexis, et al.
Publicado: (2026)

Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments
por: Li, Yuran, et al.
Publicado: (2025)

Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection
por: Song, Chengyu, et al.
Publicado: (2024)

Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
por: Hu, Yuwei, et al.
Publicado: (2024)

Auto-Prompt Ensemble for LLM Judge
por: Li, Jiajie, et al.
Publicado: (2025)

Multi-modal Synthetic Data Training and Model Collapse: Insights from VLMs and Diffusion Models
por: Hu, Zizhao, et al.
Publicado: (2025)

Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures
por: Dochkina, Victoria
Publicado: (2026)

Project Riley: Multimodal Multi-Agent LLM Collaboration with Emotional Reasoning and Voting
por: Ortigoso, Ana Rita, et al.
Publicado: (2025)

Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents
por: Yang, Jingbo, et al.
Publicado: (2026)

Agent Audit: A Security Analysis System for LLM Agent Applications
por: Zhang, Haiyue, et al.
Publicado: (2026)

LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting
por: Yang, Yu-Jie, et al.
Publicado: (2026)

SAGE: Multi-Agent Self-Evolution for LLM Reasoning
por: Peng, Yulin, et al.
Publicado: (2026)

M3PT: A Transformer for Multimodal, Multi-Party Social Signal Prediction with Person-aware Blockwise Attention
por: Tang, Yiming, et al.
Publicado: (2025)

Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
por: Ma, Chiyu, et al.
Publicado: (2025)

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
por: Saha, Swarnadeep, et al.
Publicado: (2025)

Structured Personality Control and Adaptation for LLM Agents
por: Wang, Jinpeng, et al.
Publicado: (2026)

Thought Branches: Interpreting LLM Reasoning Requires Resampling
por: Macar, Uzay, et al.
Publicado: (2025)

Thought Anchors: Which LLM Reasoning Steps Matter?
por: Bogdan, Paul C., et al.
Publicado: (2025)

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
por: Yuan, Tongxin, et al.
Publicado: (2024)

AuditAgent: Expert-Guided Multi-Agent Reasoning for Cross-Document Fraudulent Evidence Discovery
por: Bai, Songran, et al.
Publicado: (2025)

Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation
por: Huang, Tzu-Heng, et al.
Publicado: (2025)

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
por: Yuan, Wenhao, et al.
Publicado: (2026)

Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications
por: Cao, Hongliu, et al.
Publicado: (2025)