# Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents

arXiv: https://arxiv.org/abs/2505.03434 · HTML: https://mlsanity.com/paper/2505.03434/

## Key facts

- Cited by 9 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 10 of its 29 references that are in the map.
- First posted on arXiv 6 May 2025.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models](https://mlsanity.com/paper/2402.02244/) (2024)
- [On Limitations of the Transformer Architecture](https://mlsanity.com/paper/2402.08164/) (2024)
- [Understanding LLMs: A Comprehensive Overview from Training to Inference](https://mlsanity.com/paper/2401.02038/) (2024)
- [Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters](https://mlsanity.com/paper/2104.04103/) (2021)
- [Sliding-Window Thompson Sampling for Non-Stationary Settings](https://mlsanity.com/paper/2409.05181/) (2024)
- [Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting](https://mlsanity.com/paper/2410.19920/) (2024)

## Built on by (most cited first, 9 of 9)

- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying](https://mlsanity.com/paper/2604.09747/) (2026)
- [The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures](https://mlsanity.com/paper/2510.05364/) (2025)
- [A Benchmark for Procedural Memory Retrieval in Language Agents](https://mlsanity.com/paper/2511.21730/) (2025)
- [M2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval](https://mlsanity.com/paper/2603.00503/) (2026)
- [Towards autonomous normative multi-agent systems for Human-AI software engineering teams](https://mlsanity.com/paper/2512.02329/) (2025)
- [CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems](https://mlsanity.com/paper/2603.15642/) (2026)
- [Behavioural Effects of Agentic Messaging: A Case Study on a Financial Service Application](https://mlsanity.com/paper/2512.17462/) (2025)
- [Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study](https://mlsanity.com/paper/2604.08621/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) represent a landmark achievement in Artificial Intelligence (AI), demonstrating unprecedented proficiency in procedural tasks such as text generation, code completion, and conversational coherence. These capabilities stem from their architecture, which mirrors human procedural memory -- the brain's ability to automate repetitive, pattern-driven tasks through practice. However, as LLMs are increasingly deployed in real-world applications, it becomes impossible to ignore their limitations operating in complex, unpredictable environments. This paper argues that LLMs, while transformative, are fundamentally constrained by their reliance on procedural memory. To create agents capable of navigating ``wicked'' learning environments -- where rules shift, feedback is ambiguous, and novelty is the norm -- we must augment LLMs with semantic memory and associative learning systems. By adopting a modular architecture that decouples these cognitive functions, we can bridge the gap between narrow procedural expertise and the adaptive intelligence required for real-world problem-solving.