Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.01528 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917553189683200 |
|---|---|
| author | Tian, Shizuo Weng, Xiaohong Kong, Rui Chen, Yuxuan Liu, Guohong Song, Yuebing Liu, Jiacheng Li, Yuchen Yin, Dawei Cao, Ting Liu, Yunxin Li, Yuanchun |
| author_facet | Tian, Shizuo Weng, Xiaohong Kong, Rui Chen, Yuxuan Liu, Guohong Song, Yuebing Liu, Jiacheng Li, Yuchen Yin, Dawei Cao, Ting Liu, Yunxin Li, Yuanchun |
| contents | In open-ended environments, exploration is fundamental for autonomous agents, yet current language model agents struggle with this. Effective exploration requires memory, but retaining raw interaction histories is computationally expensive over long trajectories. While latent memory offers a solution to compress interaction histories, its training lacks reliable supervisory signals. We introduce \textbf{J}oint \textbf{A}gent \textbf{M}emory and \textbf{E}xploration \textbf{L}earning (\textbf{JAMEL}), a framework that trains agentic memory and exploration policy together through novelty-driven interaction. We observe that memory and exploration form a mutually dependent loop: sustained exploration requires memory to distinguish exhausted behaviors from unseen ones, while novelty-seeking interaction provides the supervision needed to make memory useful for future exploration. By utilizing deterministic and persistent novelty signals such as code coverage in the GUI domain, we provide natural, annotation-free supervision for the memory module. Empirical evaluations demonstrate that \ours successfully generalizes to unseen environments. Its exploration capability outperforms open-weight baselines and rivals the exploration depth of a closed-source model while reducing token consumption. Our code and model are open-sourced at https://github.com/MobileLLM/JAMEL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01528 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Joint Agent Memory and Exploration Learning via Novelty Signals Tian, Shizuo Weng, Xiaohong Kong, Rui Chen, Yuxuan Liu, Guohong Song, Yuebing Liu, Jiacheng Li, Yuchen Yin, Dawei Cao, Ting Liu, Yunxin Li, Yuanchun Artificial Intelligence In open-ended environments, exploration is fundamental for autonomous agents, yet current language model agents struggle with this. Effective exploration requires memory, but retaining raw interaction histories is computationally expensive over long trajectories. While latent memory offers a solution to compress interaction histories, its training lacks reliable supervisory signals. We introduce \textbf{J}oint \textbf{A}gent \textbf{M}emory and \textbf{E}xploration \textbf{L}earning (\textbf{JAMEL}), a framework that trains agentic memory and exploration policy together through novelty-driven interaction. We observe that memory and exploration form a mutually dependent loop: sustained exploration requires memory to distinguish exhausted behaviors from unseen ones, while novelty-seeking interaction provides the supervision needed to make memory useful for future exploration. By utilizing deterministic and persistent novelty signals such as code coverage in the GUI domain, we provide natural, annotation-free supervision for the memory module. Empirical evaluations demonstrate that \ours successfully generalizes to unseen environments. Its exploration capability outperforms open-weight baselines and rivals the exploration depth of a closed-source model while reducing token consumption. Our code and model are open-sourced at https://github.com/MobileLLM/JAMEL. |
| title | Joint Agent Memory and Exploration Learning via Novelty Signals |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2606.01528 |