Muyan Weng (翁牧言) | Melady Labhttps://usc-melady.github.io/melady_website/author/muyan-weng-%E7%BF%81%E7%89%A7%E8%A8%80/Muyan Weng (翁牧言)Hugo Blox Builder (https://hugoblox.com)en-usMon, 09 Mar 2026 00:00:00 +0000https://usc-melady.github.io/melady_website/author/muyan-weng-%E7%BF%81%E7%89%A7%E8%A8%80/avatar_hu11943013483242056873.jpgMuyan Weng (翁牧言)https://usc-melady.github.io/melady_website/author/muyan-weng-%E7%BF%81%E7%89%A7%E8%A8%80/Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learninghttps://usc-melady.github.io/melady_website/publication/yang-adaptive-collaboration-2026/Mon, 09 Mar 2026 00:00:00 +0000https://usc-melady.github.io/melady_website/publication/yang-adaptive-collaboration-2026/TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Taskshttps://usc-melady.github.io/melady_website/publication/weng-temporalbench-2026/Thu, 05 Feb 2026 00:00:00 +0000https://usc-melady.github.io/melady_website/publication/weng-temporalbench-2026/Toward Evolutionary Intelligence: LLM-based Agentic Systems with Multi-Agent Reinforcement Learninghttps://usc-melady.github.io/melady_website/publication/yang-evolutionary-intelligence-2025/Thu, 27 Nov 2025 00:00:00 +0000https://usc-melady.github.io/melady_website/publication/yang-evolutionary-intelligence-2025/