arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07972cs.AI
收藏

适应性协作与人类:多智能体大语言模型的元认知策略优化与持续学习

Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning

University of Southern California(南加州大学)

Wei Yang, Defu Cao, Jiacheng Pang, Muyan Weng, Yan Liu

AI总结:

HILA框架通过元认知策略优化与持续学习,实现多智能体与人类的协同协作,提升复杂任务处理能力。

摘要:

尽管单个大语言模型(LLM)的扩展已取得了显著进展,但下一步的前沿在于通过多智能体系统(MAS)扩展协作能力。然而,纯粹自主的MAS仍然是

英文摘要:

While scaling individual Large Language Models (LLMs) has delivered remarkable progress, the next frontier lies in scaling collaboration through multi-agent systems (MAS). However, purely autonomous MAS remain ''closed-world'' systems, constrained by the static knowledge horizon of pre-trained models. This limitation makes them brittle on tasks requiring knowledge beyond training data, often leading to collective failure under novel challenges. To address this, we propose the Human-In-the-Loop Multi-Agent Collaboration (HILA) framework, a principled paradigm for human--agent collaboration. HILA trains agents to learn a metacognitive policy that governs when to solve problems autonomously and when to defer to a human expert. To operationalize this policy, we introduce Dual-Loop Policy Optimization, which disentangles immediate decision-making from long-term capability growth. The inner loop applies Group Relative Policy Optimization (GRPO) with a cost-aware reward to optimize deferral decisions, while the outer loop implements continual learning, transforming expert feedback into high-quality supervised signals that strengthen the agent's reasoning ability. Experiments on challenging mathematical and problem-solving benchmarks show that HILA, equipped with Dual-Loop Policy Optimization, consistently outperforms advanced MAS, establishing a principled foundation for collaborative and continually improving agentic systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑