ניהול סוכנים מונחה עילית לשימוש יעיל ב-LLM

תקציר מקורי באנגליתarXiv:2603.19896v2 Announce Type: replace Abstract: Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. In this paper, we study agent orchestration as an explicit decision problem rather than leaving it entirely to prompt-level behavior. We propose a utility-guided orchestration policy that selects among actions such as respond, retrieve, tool call, verify, and stop by balancing estimated gain, step cost, uncertainty, and redundancy. Our goal is not to claim universally best task perfo