View publication
| Title | FALAA: Framework for the Abstraction of Language Agent Architectures |
| Authors | Nicolás Brandstetter, Felipe Bravo-Marquez, Federico Olmedo |
| Publication date | 2025 |
| Abstract | The rapid development of LLM-based language agents has led to a proliferation of architectures described using ad hoc and inconsistent methods, making it difficult to compare, reproduce, extend or even understand them. To address this, we introduce FALAA: a framework that standardizes the description of language agent architectures through a structured set of components--Planner, Executor, Evaluator, Reflector, Memory, and Environment--and a dual-level methodology combining UML diagrams and OCL specifications. \n\n FALAA offers both conceptual clarity and formal precision, enabling unambiguous definitions of agent behaviors and responsibilities. We illustrate its effectiveness through case studies of two representative agents: Reflexion and Retroformer. The formalization reveals critical ambiguities in both architectures, such as vague component definitions and underspecified memory handling. These results show how FALAA enhances clarity, supports architecture comparison, and uncovers design limitations, making it a promising tool for the development and analysis of future language agents. |
| Pages | 45-61 |
| Conference name | International Workshop on Engineering Multi-Agent Systems (EMAS) |
| Publisher | Springer Nature Switzerland AG (Cham, Switzerland) |
| Reference URL |
|