# Agents unlock new capabilities through Switching LoRA Adapters as a Tool (SLAaaT)

arXiv: https://arxiv.org/abs/2608.17034 · HTML: https://mlsanity.com/paper/2608.17034/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 11 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Specializing Smaller Language Models towards Multi-Step Reasoning](https://mlsanity.com/paper/2301.12726/) (2023)
- [Towards Modular LLMs by Building and Reusing a Library of LoRAs](https://mlsanity.com/paper/2405.11157/) (2024)
- [Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA](https://mlsanity.com/paper/2512.17910/) (2025)
- [Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay](https://mlsanity.com/paper/2605.26097/) (2026)
- [Adaptive Minds: Empowering Agents with LoRA-as-Tools](https://mlsanity.com/paper/2510.15416/) (2025)

## Abstract (arXiv)

Post-training can unlock new capabilities and improve performance on specialized tasks, but sometimes at the cost of catastrophic forgetting in other domains. This poses a problem in long agent trajectories that compose different capabilities. We reject this tradeoff by giving an agent a tool to switch between specialized LoRA adapters mid-trace. To test its effectiveness, we compose two synthetic coding tasks that are logically simple but require specialization. We find that this allows the model to solve problems it previously could not, that the model is able to switch autonomously (and find a new strategy that beats our human heuristic baseline on one task), and that this incurs an up to an 18x reduction in capability tax compared to an agent using only one specialized adapter. Our approach also substantially outperforms spawning subagents in both task capabilities (solving 4 of our hardest tasks versus none) and token usage (46.1x fewer tokens in some scenarios).