Adaptive Minds: Empowering Agents with LoRA-as-Tools
This provides a scalable and extensible solution for domain-adaptive AI assistance, though it is incremental as it combines existing techniques like multi-agent orchestration and parameter-efficient fine-tuning.
The paper tackles the problem of enabling AI agents to dynamically access domain-specific expertise by treating LoRA adapters as tools, allowing a base LLM to semantically route queries to relevant adapters, resulting in accurate and specialized responses while maintaining conversational ability.
We present Adaptive Minds, an agentic system that treats LoRA adapters as domain-specific tools. Instead of relying on a single fine-tuned model or rigid rule-based routing, our approach empowers the base LLM itself to act as a semantic router analyzing each query and dynamically selecting the most relevant LoRA tool. This enables the agent to seamlessly switch between different domain experts on demand. By combining the flexibility of multi-agent orchestration with the efficiency of parameter-efficient fine-tuning, Adaptive Minds delivers accurate, specialized responses while preserving conversational ability. The system is built with LangGraph for workflow management, supports both API and web interfaces, and is fully open source, providing a scalable and extensible foundation for domain-adaptive AI assistance.