Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
For LLM agent developers, NPM offers a new method to embed procedural memory without explicit text, addressing the text-action disconnect in current RAG-based approaches.
The paper introduces Neural Procedural Memory (NPM), a training-free framework that uses implicit activation steering instead of explicit instructions to provide procedural memory for LLM agents. NPM achieves comparable performance to explicit instruction baselines across four agent benchmarks, and combining both approaches yields more robust task execution.
While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interaction, yet current agents lack the necessary persistent procedural memory. Existing approaches predominantly employ Retrieval-Augmented Generation (RAG) to inject explicit textual guidelines into model contexts. However, relying solely on symbolic instructions can introduce a text-action disconnect, frequently failing to activate the internal representations necessary for correct task execution. To address this, the paper introduces Neural Procedural Memory (NPM), a training-free framework that represents agent memory through implicit activation steering rather than explicit instructions. By distilling procedural skills from historical contrastive experiences into steering vectors in the activation space, NPM directly activates the task-relevant neural mechanisms to guide task execution. Evaluations across four agent benchmarks show that NPM performs comparably to baselines using explicit textual instructions. Furthermore, the results show that combining implicit steering with explicit workflows provides complementary advantages, leading to more robust task execution. Representational analyses indicate that these steering vectors encode consistent task logic, forming organized structures within the activation space. These findings suggest that implicit activation steering provides a promising approach for managing agent memory.