Tag: multi-agent
All the articles with the tag "multi-agent".
- 6.5
EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
EvoAgent将技能建模为多文件结构化能力单元，支持触发机制和进化元数据。
- 6.3
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
通过文本参数图(TPG)优化实现多Agent系统的自改进，赋予优化器从经验中学习的能力。
- 7.3
More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems
致敬Anderson的经典论文，探讨AI原生软件生态系统中的涌现理论——个体正确但整体失效的根本挑战。
- 6.0
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
RADAR：角色锚定多智能体辩论框架，针对遗漏式操纵（半真半假）的事实核查新方法
- 6.0
Mango: Multi-Agent Web Navigation via Global-View Optimization
Mango：利用网站全局结构动态确定最优导航路径的多智能体Web导航方法
- 5.4
SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
SkillForge 提出面向企业云技术支持场景的 domain-specific agent 技能自演化框架，通过追踪执行失败并反溯到技能缺陷来驱动持续精炼。
- 5.3
Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
受人类认知发展中师生互动启发，提出 Tutor-Student 多 agent 交互框架，通过结构化的角色对话推动 LLM 超越单 agent 性能上限。
- 6.4
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
arXiv:2604.06091v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly acting as human delegates in multi-agent envir...
- 6.4
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo
arXiv:2604.05681v1 Announce Type: cross Abstract: We introduce LudoBench, a benchmark for evaluating LLM strategic reasoning in Ludo, a stochastic ...
- 6.4
Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning
arXiv:2604.05483v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown a high capability in answering questions on a diverse ran...
- 6.4
MMORF: A Multi-agent Framework for Designing Multi-objective Retrosynthesis Planning Systems
arXiv:2604.05075v1 Announce Type: cross Abstract: Multi-objective retrosynthesis planning is a critical chemistry task requiring dynamic balancing ...
- 6.4
MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning
arXiv:2604.05943v1 Announce Type: new Abstract: Recent advances in multi-agent reinforcement learning (MARL) have demonstrated success in numerous ...
- 6.4
MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library
arXiv:2604.05458v1 Announce Type: cross Abstract: Network Intrusion Detection Systems (NIDS) face important limitations. Signature-based methods ar...
- 5.6
Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework
arXiv:2604.06170v1 Announce Type: new Abstract: The rapid growth of scientific literature has made it increasingly difficult for researchers to eff...
- 6.6
TradingAgents：模拟真实交易公司的多 Agent LLM 金融交易框架
基于 LangGraph 的开源多 Agent 金融交易框架，部署基本面分析、情绪分析、技术分析等专职 Agent 协作完成交易决策。
- 7.2
Spine Swarm：可视化画布上的多智能体协作系统
YC S23 项目 Spine Swarm 展示多智能体在无限可视化画布上协作完成复杂非编程项目的新范式
- 8.5
OpenAI Codex 正式发布 Subagents 功能，编程 Agent 进入多智能体时代
Codex Subagents GA，支持自定义 Agent（TOML 配置）和多 Agent 并行协作，Subagents 模式已成为编程 Agent 标配
- 7.0
MiroFish：简洁通用的群体智能引擎，今日 GitHub 热榜第一
666ghj/MiroFish 今日 GitHub 热榜新增 2,907 星，是一个可预测任意领域的群体智能引擎，融合多 agent 协作与集体决策机制。
- 7.8
论文：将 LLM 团队视为分布式系统
arXiv 新论文提出用分布式系统理论指导 LLM 团队设计，解决何时需要团队、多少 Agent、结构如何影响性能等核心问题
- 8.0
USC 研究：LLM Agent 网络会自发协调宣传行动，无需人类指挥
南加大研究发现，互联的 LLM Agent 网络能自发涌现出协调一致的宣传策略，没有任何显式的「传播指令」——这是 AI 安全的一个新型风险面向。