Imagen de Portada

Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Yongqiang, Niu, Gang, Cheng, James, Han, Bo, Sugiyama, Masashi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Scalable Oversight via Partitioned Human Supervision
por: Yin, Ren, et al.
Publicado: (2025)

Knowledge Divergence and the Value of Debate for Scalable Oversight
por: Young, Robin
Publicado: (2026)

BrokenBind: Universal Modality Exploration beyond Dataset Boundaries
por: Huang, Zhuo, et al.
Publicado: (2026)

What Is Preference Optimization Doing, and Why?
por: Wang, Yue, et al.
Publicado: (2025)

Decoupling the Class Label and the Target Concept in Machine Unlearning
por: Zhu, Jianing, et al.
Publicado: (2024)

Rethinking Consistent Multi-Label Classification Under Inexact Supervision
por: Wang, Wei, et al.
Publicado: (2025)

Exploring Health Misinformation Detection with Multi-Agent Debate
por: Chen, Chih-Han, et al.
Publicado: (2025)

A Fast Algorithm for the Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
por: Nakamura, Shintaro, et al.
Publicado: (2023)

Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning
por: Xiao, Jia-Hao, et al.
Publicado: (2024)

Multi-Player Approaches for Dueling Bandits
por: Raveh, Or, et al.
Publicado: (2024)

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
por: Wang, Qizhou, et al.
Publicado: (2024)

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation
por: Xu, Jie, et al.
Publicado: (2025)

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
por: Wang, Wei, et al.
Publicado: (2023)

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
por: Zhang, Zhen-Yu, et al.
Publicado: (2024)

VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates
por: Braun, Guillaume, et al.
Publicado: (2024)

How Interpretable Are Interpretable Graph Neural Networks?
por: Chen, Yongqiang, et al.
Publicado: (2024)

Multi-Agent Debate with Memory Masking
por: Tian, Hongduan, et al.
Publicado: (2026)

VerificAgent: Domain-Specific Memory Verification for Scalable Oversight of Aligned Computer-Use Agents
por: Nguyen, Thong Q., et al.
Publicado: (2025)

In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement
por: Zhang, Zhen-Yu, et al.
Publicado: (2024)

Towards Understanding Valuable Preference Data for Large Language Model Alignment
por: Zhang, Zizhuo, et al.
Publicado: (2025)

From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
por: Yi, Xie, et al.
Publicado: (2025)

Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
por: Wang, Wei, et al.
Publicado: (2025)

A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection
por: Enouen, James, et al.
Publicado: (2024)

Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents
por: Tran, Quan M., et al.
Publicado: (2026)

Scaling Laws For Scalable Oversight
por: Engels, Joshua, et al.
Publicado: (2025)

Balancing Similarity and Complementarity for Federated Learning
por: Yan, Kunda, et al.
Publicado: (2024)

Accurate Forgetting for Heterogeneous Federated Continual Learning
por: Wuerkaixi, Abudukelimu, et al.
Publicado: (2025)

Realistic Evaluation of Deep Partial-Label Learning Algorithms
por: Wang, Wei, et al.
Publicado: (2025)

Multi-Label Knowledge Distillation
por: Yang, Penghui, et al.
Publicado: (2023)

Steering LLMs via Scalable Interactive Oversight
por: Zhou, Enyu, et al.
Publicado: (2026)

Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
por: Xie, Ming-Kun, et al.
Publicado: (2024)

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
por: Cai, Xin-Qiang, et al.
Publicado: (2025)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
por: Zhan, Zhiyuan, et al.
Publicado: (2026)

Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
por: Zhang, Yivan, et al.
Publicado: (2023)

Practical estimation of the optimal classification error with soft labels and calibration
por: Ushio, Ryota, et al.
Publicado: (2025)

The Survival Bandit Problem
por: Riou, Charles, et al.
Publicado: (2022)

Thompson Exploration with Best Challenger Rule in Best Arm Identification
por: Lee, Jongyeong, et al.
Publicado: (2023)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
por: Cai, Xin-Qiang, et al.
Publicado: (2026)

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
por: Chen, Zhikang, et al.
Publicado: (2025)

Modeling Human Beliefs about AI Behavior for Scalable Oversight
por: Lang, Leon, et al.
Publicado: (2025)