**摘要**
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with modern structured agent workflows, in which independent branches explore subtasks, retrieve evidence, or generate candidate solutions before a final synthesis step. Existing systems typically merge these branches by conc
👤 作者: Shikun Liu, MUFEI LI, Dongqi Fu, Haoyu Wang, Yinglong Xia, Hong Li, Hong Yan, Pan Li

---
🔗 **[在LLM-Agent工作流程中实现并行分支的直接潜空间合成](https://arxiv.org/abs/2606.14672v1)**

> Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-15 14:01