Year: 2026
Type: conference-paper
Abstract: Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.In this work, we investigate strategies to endow agents with a learnable, updatable, and lifelong procedural memory.We propose M em p that distills past agent trajectories into both finegrained, step-by-step instructions and higherlevel, script-like abstractions, and explore the impact of different strategies for Build, Retrieval, and Update of procedural memory.Coupled with a dynamic regimen that continuously updates, corrects, and deprecates its contents, this repository evolves in lockstep with new experience.Empirical evaluation on TravelPlanner and ALFWorld shows that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks.Moreover, procedural memory built from a stronger model retains its value: migrating the procedural memory to a weaker model can also yield substantial performance gains.
Institutions: Alibaba Group (China), Zhejiang University, Nanjing University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G4648959265
OpenAlex ID: W4416872027