# A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents

arXiv: https://arxiv.org/abs/2510.18608 · HTML: https://mlsanity.com/paper/2510.18608/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI](https://mlsanity.com/paper/2410.00425/) (2024)
- [Instruction-driven history-aware policies for robotic manipulations](https://mlsanity.com/paper/2209.04899/) (2022)
- [The Future of Continual Learning in the Era of Foundation Models: Three Key Directions](https://mlsanity.com/paper/2506.03320/) (2025)
- [Has LLM Reached the Scaling Ceiling Yet? Unified Insights into LLM Regularities and Constraints](https://mlsanity.com/paper/2412.16443/) (2024)
- [Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning](https://mlsanity.com/paper/2507.07197/) (2025)
- [GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging](https://mlsanity.com/paper/2509.13211/) (2025)

## Abstract (arXiv)

The birth of Foundation Models brought unprecedented results in a wide range of tasks, from language to vision, to robotic control. These models are able to process huge quantities of data, and can extract and develop rich representations, which can be employed across different domains and modalities. However, they still have issues in adapting to dynamic, real-world scenarios without retraining the entire model from scratch. In this work, we propose the application of Continual Learning and Compositionality principles to foster the development of more flexible, efficient and smart AI solutions.