README.md

---
license: mit
library_name: transformers
pipeline_tag: text-generation
---

# MemHarness: Memory Is Reconstructed, Not Replayed

This repository contains the model described in [MemHarness: Memory Is Reconstructed, Not Replayed](https://huggingface.co/papers/2607.28272).

**Paper**: [arXiv](https://arxiv.org/abs/2607.28272) | [Hugging Face Paper](https://huggingface.co/papers/2607.28272)

**Code**: [https://github.com/KnowledgeXLab/MemHarness](https://github.com/KnowledgeXLab/MemHarness)

## Description

MemHarness is a framework that equips LLM agents to actively harness and reconstruct past experiences based on the present context — instead of replaying retrieved memories verbatim. This model is a Qwen2.5-7B-Instruct based model fine-tuned with GRPO for memory-augmented decision making in agentic tasks such as ALFWorld and WebShop. It demonstrates state-of-the-art performance in both in-distribution and out-of-distribution scenarios.

Please refer to the [paper](https://arxiv.org/abs/2607.28272) for full details.