| title | Mem-π: Adaptive Memory through Learning When and What to Generate |
|---|---|
| authors | Xiaoqiang Wang, Chao Wang, Hadi Nekoei, Christopher Pal, Alexandre Lacoste, Spandana Gella, Bang Liu, Perouz Taslakian |
| date | 2026-05-20 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.21463 |
| upvotes | 6 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We present Mem-π, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on similarity-based retrieval from episodic memory banks or skill libraries, returning static entries that often misalign with the current context. In contrast, Mem-π uses a dedicated language or vision-language model with its own parameters, separate from the downstream agent, to generate context-specific guidance for complex tasks. Conditioned on the current agent context, the model jointly decides when to produce guidance and what guidance to produce. We train it with a decision-content decoupled reinforcement learning (RL) objective, enabling it to abstain when generation would not help and otherwise produce concise, useful guidance. Across diverse agentic benchmarks spanning web navigation, terminal-based tool use, and text-based embodied interaction, Mem-π consistently outperforms retrieval-based and prior RL-optimized memory baselines, achieving over 30% relative improvement on web navigation tasks. |
cite
@misc{wang2026mem,
title={Mem-π: Adaptive Memory through Learning When and What to Generate},
author={Xiaoqiang Wang and Chao Wang and Hadi Nekoei and Christopher Pal and Alexandre Lacoste and Spandana Gella and Bang Liu and Perouz Taslakian},
year={2026},
eprint={2605.21463},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.21463}
}