[2510.26389] Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning

Computer Science > Machine Learning arXiv:2510.26389 (cs) [Submitted on 30 Oct 2025 (v1), last revised 1 Mar 2026 (this version, v2)] Title:Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning Authors:Wenchang Duan, Yaoliang Yu, Jiwan He, Yi Shi View a PDF of the paper titled Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning, by Wenchang Duan and 3 other authors View PDF HTML (experimental) Abstract:Recently, deep multi-agent reinforcement learning (MARL) has demonstrated promising performance for solving challenging tasks, such as long-term dependencies and non-Markovian environments. Its success is partly attributed to conditioning policies on large fixed context length. However, such large fixed context lengths may lead to limited exploration efficiency and redundant information. In this paper, we propose a novel MARL framework to obtain adaptive and effective contextual information. Specifically, we design a central agent that dynamically optimizes context length via temporal gradient analysis, enhancing exploration to facilitate convergence to global optima in MARL. Furthermore, to enhance the adaptive optimization capability of the context length, we present an efficient input representation for the central agent, which effectively filters redundant information. By leveraging a Fourier-based low-frequency truncation method, we extract global temporal trends ac...