新框架“传染张量”量化多智能体LLM的输出分布耦合，并衍生出耦合放大因子用于审计系统声称。
arXiv:2606.28839v1 Announce Type: new Abstract: We introduce the Contagion Tensor, a measurement framework for quantifying how large language model (L…
揭示多智能体LLM中评估偏差像病毒一样通过网络传播，影响AI协作的可靠性。
arXiv:2606.20493v1 Announce Type: cross Abstract: When large language models serve as evaluators in multi-agent systems, their systematic evaluation b…
多智能体LLM协调稳定性新方案：熵正则化均衡选择，突破传统博弈论限制。
arXiv:2606.08068v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model…
论文揭示多智能体LLM系统拓扑结构如何引发记忆泄漏，并提出MAMA评估框架量化风险。
arXiv:2512.04668v4 Announce Type: replace-cross Abstract: Graph topology is a fundamental determinant of memory leakage in multi-agent LLM systems, ye…
一项研究揭示多智能体LLM架构不仅影响代码正确性，还会改变代码的结构复杂度。
arXiv:2606.00308v1 Announce Type: cross Abstract: Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestra…
多智能体LLM系统计算浪费的早期诊断方案，故障感知可观测性提升效率
arXiv:2606.01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool…
揭秘多智能体LLM系统中域伪装注入攻击如何绕过安全防护，揭示现有检测器的盲区。
arXiv:2605.22001v1 Announce Type: cross Abstract: Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads…
多智能体LLM工作流的离线评估与迭代优化新框架，即将亮相ACL 2026，助力复杂协作场景调优。
arXiv:2605.18032v1 Announce Type: new Abstract: Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform …
提出数据流导向的强化学习框架，降低智能体LLM训练成本并支持多策略协同，大幅提升可扩展性。
arXiv:2605.15565v1 Announce Type: cross Abstract: Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capa…
针对多智能体LLM协调中序列微调导致上下文分布偏移的缺陷，提出信任区域微调方法，有效提升团队协同表现。
arXiv:2605.15207v1 Announce Type: new Abstract: Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they o…