Collaborative Optimization for Agent Swarms through Flow Networks
❗Please Read❗
This is not a seminar! Participants are to read the material in advance to engage more fully with the technical and methodological details during the session.
If you have your own research, experience or saw something on the internet (blogpost, article etc.) that would add to the discussion, do contribute!
Suggested Pre-Reading:
Main paper:
Lineage papers:
Multi-agent systems extend large language models (LLMs) by decomposing complex tasks into specialized subtasks handled by different agents. However, their effectiveness is often limited by error propagation arising from suboptimal workflows and imperfect intermediate outputs.
Zheng Wang will present MANGO (Multi-Agent Network Gradient Optimization), a data-driven framework that models agent collaboration as a flow network built from successful historical workflows. MANGO integrates reinforcement learning with textual gradient signals to jointly optimize workflow structures and agent behaviours, and introduces a skipping mechanism to improve optimization efficiency.
More About the Host
Zheng Wang is currently Assistant Chief Expert at Huawei Singapore Research Center under the TopMinds program. He received his PhD from Nanyang Technological University, Singapore. His current research interests focus on AI Agents, including retrieval-augmented generation, agent planning, and multimodality. He has published over 40 papers in top-tier AI and data science conferences and journals. His research has been recognized by the ACM SIGSPATIAL China Rising Star Award, Outstanding PhD Thesis Award, WAIC Yunfan Award, Google PhD Fellowship, and AISG PhD Fellowship.
More About the Series
Paper Club is Lorong AI’s community-driven initiative where members gather to discuss and analyze academic papers, research articles, or key developments in artificial intelligence.
Get involved: Learn more about Lorong AI | Speaker Sign-up | WhatsApp Community | LinkedIn | X