English(EN)Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization
新研究优化LLM智能体工作流的成本和效率
作者PulseAugur 编辑部·[7 个来源]·
多篇研究论文正在探索优化大型语言模型（LLM）中多智能体工作流的方法，通过根据成本和能力智能地将任务路由到不同的模型层级。InFlowOp和MoFlow分别专注于无标签的成本优化和多目标生成。Planner-as-Router (PaR)和AgentRouter通过将模型选择直接集成到规划过程中来解决这个问题，目标是与仅使用前沿模型相比，显著降低成本。这些方法有望通过动态匹配任务复杂性与适当的模型层级，使LLM智能体系统更高效、更具成本效益。
AI
arXiv:2610.01017v1 Announce Type: new Abstract: Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such a workflow well remains challenging: how finely to divide the t…
arXiv:2610.01882v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) provides a powerful framework for learning coordinated behaviors through interactions with the environment. Developing MARL policies requires balancing expressive modeling of complex and m…
arXiv:2609.38294v1 Announce Type: new Abstract: We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. Existing methods for workflow generation typically optimize accuracy alone or a we…
Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such a workflow well remains challenging: how finely to divide the task, which agent to trust with each subtask, and…
Running large language model (LLM) agents in production gets expensive fast. A frontier model (the largest, most capable tier) is accurate but can cost 25 times what a small model costs per token, and the gap compounds once a workflow chains several calls together. Planner-as-Rou…
Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic wor…
HN — claude cli stories
TIER_1English(EN)·adchurch·
