Cover Image

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jianze, Liu, Ying, Chen, Jinlong, Hu, Xuchun, Zhang, Qilong, Cao, Yu, Wang, Jun, Yang, Hua, Xie, Yong, Chen, Qianglong
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System
by: Wang, Haotian, et al.
Published: (2023)

Flow-OPD: On-Policy Distillation for Flow Matching Models
by: Fang, Zhen, et al.
Published: (2026)

S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency
by: Zeng, Yuting, et al.
Published: (2025)

OPD+: Rethinking the Advantage Design for On-Policy Distillation
by: Zhao, Hanyang, et al.
Published: (2026)

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
by: Zhang, Yaolun, et al.
Published: (2026)

Free-MAD: Consensus-Free Multi-Agent Debate
by: Cui, Yu, et al.
Published: (2025)

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
by: Hou, Wenjin, et al.
Published: (2026)

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
by: Zhou, Yuhang, et al.
Published: (2026)

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation
by: Li, Zhenghao, et al.
Published: (2026)

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
by: Cao, Di, et al.
Published: (2026)

Draft-OPD: On-Policy Distillation for Speculative Draft Models
by: Lei, Haodi, et al.
Published: (2026)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
by: Yang, Zhicheng, et al.
Published: (2026)

Is Multi-Agent Debate (MAD) the Silver Bullet? An Empirical Analysis of MAD in Code Summarization and Translation
by: Chun, Jina, et al.
Published: (2025)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
by: Li, Quanhao, et al.
Published: (2026)

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
by: Chen, Xianwei, et al.
Published: (2026)

DP-OPD: Differentially Private On-Policy Distillation for Language Models
by: Khadem, Fatemeh, et al.
Published: (2026)

One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation
by: Li, Jianze, et al.
Published: (2025)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
by: Yuan, Qianhao, et al.
Published: (2026)

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
by: Huang, ShiYing, et al.
Published: (2026)

EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation
by: Lazaridis, Aristotelis, et al.
Published: (2026)

Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents
by: Wang, Zhixiang, et al.
Published: (2026)

Breaking Event Rumor Detection via Stance-Separated Multi-Agent Debate
by: Zhang, Mingqing, et al.
Published: (2024)

MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection
by: Lakara, Kumud, et al.
Published: (2024)

M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation
by: Feng, Zhaopeng, et al.
Published: (2024)

MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs
by: Ning, Yucheng, et al.
Published: (2025)

Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy
by: Liu, Yuhan, et al.
Published: (2026)

Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
by: Yuan, Yurun, et al.
Published: (2026)

M3MAD-Bench: Are Multi-Agent Debates Really Effective Across Domains and Modalities?
by: Li, Ao, et al.
Published: (2026)

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
by: Cui, Yu, et al.
Published: (2025)

Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
by: Wu, Yecheng, et al.
Published: (2026)

VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
by: Zhong, Zhide, et al.
Published: (2026)

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
by: Wang, Xiaohui, et al.
Published: (2025)

iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference
by: Fan, Wei, et al.
Published: (2025)

Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
by: Li, Jiaze, et al.
Published: (2026)

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

Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
by: Smit, Andries, et al.
Published: (2023)

CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate
by: Sun, Yiliu, et al.
Published: (2025)

Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate
by: Wang, Cunda, et al.
Published: (2026)

Mixed Distillation Helps Smaller Language Model Better Reasoning
by: Li, Chenglin, et al.
Published: (2023)

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