AAMAS Conference 2026 Conference Paper
LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
- Dongge Han
- Camille Couturier
- Daniel Madrigal Diaz
- Xuchao Zhang
- Victor Rühle
- Saravan Rajmohan
WeintroduceLEGOMem, amodularproceduralmemoryframework for multi-agent LLM systems in workflow automation. LEGOMem distills successful executions into reusable full-task and subtask memories and allocates them to orchestrators and task agents to improve planning and execution. Across three retrieval variants, experiments on OfficeBench show consistent gains of 12–13 absolute points over memory-less and baseline methods, highlighting the importance of procedural memory for workflow automation.