# PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

arXiv: https://arxiv.org/abs/2605.27762 · HTML: https://mlsanity.com/paper/2605.27762/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 20 of 20)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models](https://mlsanity.com/paper/2311.05997/) (2023)
- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks](https://mlsanity.com/paper/2408.03615/) (2024)
- [Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers](https://mlsanity.com/paper/2603.07670/) (2026)
- [Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation](https://mlsanity.com/paper/2409.18313/) (2024)
- [Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning](https://mlsanity.com/paper/2506.11672/) (2025)
- [CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion](https://mlsanity.com/paper/2601.09512/) (2026)
- [LumiVideo: An Intelligent Agentic System for Video Color Grading](https://mlsanity.com/paper/2604.02409/) (2026)
- [Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models](https://mlsanity.com/paper/2605.06010/) (2026)

## Built on by (most cited first, 2 of 2)

- [Continual Learning in Transition](https://mlsanity.com/paper/2608.06216/) (2026)
- [When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization](https://mlsanity.com/paper/2610.15492/) (2026)

## Abstract (arXiv)

We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience. PEAM pairs a slow deliberative LLM for open-ended reasoning with a fast parametric module for reflexive execution of consolidated skills. The fast module is a multimodal Mixture-of-Experts LoRA architecture with per-category physically isolated adapters, enabling parameter-level continual learning without catastrophic forgetting. We treat failure as a first-class training signal: failure--correction trajectory pairs are internalized through a joint behavioral-cloning and contrastive objective, so the agent learns not only what succeeds but also how corrected actions differ from failed ones. To govern consolidation, PEAM introduces a parameterization-worthiness score for deciding which experience should be internalized, and a scale-free self-triggered consolidation mechanism for deciding when to internalize without task-specific hand-tuned thresholds, making the agent self-evolving as the trigger transfers across task distributions without re-tuning. Experiments in Minecraft show that PEAM improves long-horizon task performance, mitigates forgetting on previously consolidated skills, and improves parametric-versus-retrieval efficiency over retrieval-based embodied agents and parametric memory variants.