The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Luoxi, Meng, Yuqiao, Costa, Joseph, Zhang, Yingxue, Ye, Muchao, Xi, Zhaohan
Format:	Preprint
Published:	2026
Subjects:	Multiagent Systems Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
by: Meng, Yuqiao, et al.
Published: (2026)

Smart Privacy Policy Assistant: An LLM-Powered System for Transparent and Actionable Privacy Notices
by: Kalvakuntla, Sriharshini, et al.
Published: (2026)

POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment
by: Tang, Luoxi, et al.
Published: (2025)

Adversarial Network Imagination: Causal LLMs and Digital Twins for Proactive Telecom Mitigation
by: Sriram, Vignesh, et al.
Published: (2026)

Schema-Grounded LLM Extraction for FHIR Patient Digital Twins
by: Brens, Rafael, et al.
Published: (2026)

SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use
by: Desai, Pratyush, et al.
Published: (2026)

Improving Clinical Data Accessibility Through Automated FHIR Data Transformation Tools
by: Pawar, Adarsh, et al.
Published: (2026)

Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
by: Qiao, Dan, et al.
Published: (2026)

Debate-Driven Multi-Agent LLMs for Phishing Email Detection
by: Nguyen, Ngoc Tuong Vy, et al.
Published: (2025)

Heterogeneous Value Decomposition Policy Fusion for Multi-Agent Cooperation
by: Wang, Siying, et al.
Published: (2025)

Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization
by: Fan, Yijia, et al.
Published: (2025)

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

Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
by: Wu, Haolun, et al.
Published: (2025)

Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty
by: Yang, Jing, et al.
Published: (2026)

Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction
by: Chen, Xi, et al.
Published: (2025)

Generalized Per-Agent Advantage Estimation for Multi-Agent Policy Optimization
by: Kim, Seongmin, et al.
Published: (2026)

AgenticPrecoding: LLM-Empowered Multi-Agent System for Precoding Optimization
by: Yang, Zijiu, et al.
Published: (2026)

Distributed Task Allocation for Multi-Agent Systems: A Submodular Optimization Approach
by: Liu, Jing, et al.
Published: (2024)

TVDO: Tchebycheff Value-Decomposition Optimization for Multi-Agent Reinforcement Learning
by: Hu, Xiaoliang, et al.
Published: (2023)

Multi-Agent Guided Policy Optimization
by: Li, Yueheng, et al.
Published: (2025)

Debate2Create: Robot Co-design via Multi-Agent LLM Debate
by: Qiu, Kevin, et al.
Published: (2025)

Policy Optimization in Multi-Agent Settings under Partially Observable Environments
by: Zhaikhan, Ainur, et al.
Published: (2025)

MARPO: A Reflective Policy Optimization for Multi Agent Reinforcement Learning
by: Wu, Cuiling, et al.
Published: (2025)

Multi-LLM Systems Exhibit Robust Semantic Collapse
by: Kong, Weiyi, et al.
Published: (2026)

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

Synthesis of Communication Policies for Multi-Agent Systems Robust to Communication Restrictions
by: Soudijani, Saleh, et al.
Published: (2025)

Mitigating Side Effects in Multi-Agent Systems Using Blame Assignment
by: Rustagi, Pulkit, et al.
Published: (2024)

ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
by: Liu, Jinnuo, et al.
Published: (2026)

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

Towards a Distributed Platform for Normative Reasoning and Value Alignment in Multi-Agent Systems
by: Garcia-Bohigues, Miguel, et al.
Published: (2024)

Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
by: Liu, Xiaoqun, et al.
Published: (2024)

Conformal Off-Policy Prediction for Multi-Agent Systems
by: Kuipers, Tom, et al.
Published: (2024)

Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
by: Liu, Yiqing, et al.
Published: (2026)

LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learning
by: Wu, Xiaoguang, et al.
Published: (2026)

Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
by: Yu, Xinlei, et al.
Published: (2025)

B2MAPO: A Batch-by-Batch Multi-Agent Policy Optimization to Balance Performance and Efficiency
by: Zhang, Wenjing, et al.
Published: (2024)

Query Optimization Beyond Data Systems: The Case for Multi-Agent Systems
by: Kaoudi, Zoi, et al.
Published: (2025)

OPTIMA: Optimized Policy for Intelligent Multi-Agent Systems Enables Coordination-Aware Autonomous Vehicles
by: Du, Rui, et al.
Published: (2024)

INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
by: Zhou, Yijin, et al.
Published: (2026)

Self-Evolving Multi-Agent Systems via Decentralized Memory
by: Hao, Guangya, et al.
Published: (2026)