AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple agents, yet their performance depends on the prompt design of each agent. For MAS prompt optimization, textual gradient methods that guide prompt updates using natural-language feedback have emerged as a leading paradigm. In this paper, we identify limitations in two stages of existing textual gradient approaches: gradient extraction and gradient aggregation. In gradient extraction, previous works select a target prompt without verifying whether modifying it resolves the failure, and derive gradients without agent-level supervision over the corresponding agent’s intermediate output. In gradient aggregation, individual gradients are randomly grouped and concatenated, often mixing unrelated failure modes and producing prompts that fail to generalize. To address these limitations, we propose AgentGrad, a prompt optimization framework for multi-agent systems based on sequential intervention and semantic textual gradient abstraction. For each failure, sequential intervention modifies the behavior of one agent at a time to identify the target agent whose modification resolves the failure.

Introduction. Recent advances in large language models (LLMs) have enabled the development of multi-agent systems (MAS), where multiple LLM-powered agents interact to solve complex tasks [1–4]. A key advantage of MAS is that they decompose difficult problems into subtasks, allowing different agents to contribute complementary capabilities [1–3]. Such systems have shown strong performance across a wide range of challenging settings, including multi-step reasoning, planning, and information synthesis [1, 3–6]. The behavior of each agent is governed by its input prompt, making prompt design critical to system performance [7, 8]. Motivated by this, recent works have explored automatic prompt optimization for MAS showing that refining agent prompts can substantially improve system performance [7–13]. Among these, textual gradient methods, which employ natural-language feedback to iteratively refine prompts, have emerged as a leading paradigm. [9–11, 14, 15].

Discussion / Conclusion. We propose AgentGrad, a prompt optimization framework for multi-agent systems that addresses systematic limitations in two stages of existing textual gradient approaches: gradient extraction and gradient aggregation. AgentGrad introduces sequential intervention, which identifies the agent responsible for each failure and produces an agent-level pseudo-label as fine-grained supervision for gradient extraction. Next, AgentGrad introduces semantic textual gradient abstraction, which clusters sample-level gradients into semantic minibatches sharing a corrective pattern and abstracts each cluster into a single generalized gradient with improved generalizability. Across five MAS benchmarks spanning multi-hop QA, claim verification, instruction following, privacy-conscious delegation, and math reasoning, AgentGrad achieves state-of-the-art performance with both GPT-5-mini and Qwen3-8B, outperforming MIPROv2, TextGrad, and GEPA while reducing wall-clock optimization time by 2.5× on average over the next-fastest baseline.