无需训练即可编排多模态大模型，实现零样本协调多种能力，降低落地门槛
arXiv:2508.10016v4 Announce Type: replace Abstract: Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse…
将Agent工作流编译进LLM权重，以极低成本实现接近前沿的质量，提出了一种颠覆性的模型优化路径。
arXiv:2605.22502v1 Announce Type: new Abstract: Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across L…
提出PlexRL框架，在集群层面编排服务化LLM执行以优化RLVR，显著提升推理效率与资源利用率
arXiv:2605.20863v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has recently unlocked strong reasoning capabil…
提出Flow-Driven递归技能进化框架，解决智能体编排中策略崩溃与信用分配难题，为LLM智能体自动化复杂任务提供新思路。
arXiv:2605.14089v1 Announce Type: new Abstract: In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex…
GraphBit用有向无环图取代大模型自编排，彻底根治幻觉路由与无限循环，AI工作流走向确定性执行。
arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow…
首个系统化微服务架构实战，解决OCR与LLM管线生产部署难题，权威论文直击文档AI落地关键。
arXiv:2605.18818v1 Announce Type: cross Abstract: Academic research tends to focus on new models for document understanding creating a wide gap in the…
多模态代理平台MediaClaw提出三层架构，解决AIGC部署碎片化痛点，技术报告首发。
arXiv:2605.14771v1 Announce Type: new Abstract: MediaClaw is a multimodal agent platform built on the OpenClaw ecosystem. Its core design follows a th…
Amazon Bedrock 推出有状态代理运行时，为多步骤 AI 工作流带来持久编排、记忆与安全执行能力。
Stateful Runtime for Agents in Amazon Bedrock brings persistent orchestration, memory, and secure execution to multi-step AI workflows powered by Open…
从桌面应用直接编排多智能体工作流，Google Antigravity 2.0 让复杂协作变得简单直观。
Orchestrate multi-agent workflows from a desktop app Discussion | Link