# Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

arXiv: https://arxiv.org/abs/2606.29824 · HTML: https://mlsanity.com/paper/2606.29824/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)
- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 28 of 28)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control](https://mlsanity.com/paper/2306.07863/) (2023)
- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization](https://mlsanity.com/paper/2308.02151/) (2023)
- [MemGen: Weaving Generative Latent Memory for Self-Evolving Agents](https://mlsanity.com/paper/2509.24704/) (2025)
- [The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs](https://mlsanity.com/paper/2509.09677/) (2025)
- [LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation](https://mlsanity.com/paper/2510.04851/) (2025)
- [Multi-property Steering of Large Language Models with Dynamic Activation Composition](https://mlsanity.com/paper/2406.17563/) (2024)
- [Control Illusion: The Failure of Instruction Hierarchies in Large Language Models](https://mlsanity.com/paper/2502.15851/) (2025)
- [AI PERSONA: Towards Life-long Personalization of LLMs](https://mlsanity.com/paper/2412.13103/) (2024)
- [Base Models Know How to Reason, Thinking Models Learn When](https://mlsanity.com/paper/2510.07364/) (2025)
- [Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models](https://mlsanity.com/paper/2407.08440/) (2024)
- [Self-Updatable Large Language Models by Integrating Context into Model Parameters](https://mlsanity.com/paper/2410.00487/) (2024)
- [BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions](https://mlsanity.com/paper/2510.10666/) (2025)
- [A Machine with Short-Term, Episodic, and Semantic Memory Systems](https://mlsanity.com/paper/2212.02098/) (2022)

## Built on by (most cited first, 3 of 3)

- [MemTools: A Unified Research Framework for Interoperable Agent Memory](https://mlsanity.com/paper/2607.21404/) (2026)
- [Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks](https://mlsanity.com/paper/2609.09774/) (2026)
- [What Survives When Activation Steering Is Used as Memory](https://mlsanity.com/paper/2610.14958/) (2026)

## Abstract (arXiv)

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.