---
title: "MobileLLM's JAMEL Teaches AI Agents to Explore Unfamiliar Apps Without Human Labels"
subtitle: "JAMEL trains GUI agents to explore and remember simultaneously, using JavaScript code coverage as a free training signal — no human labels needed."
url: "https://alphasignal.ai/news/mobilellm-s-jamel-teaches-ai-agents-to-explore-unfamiliar-apps-without-human"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-01T00:00:00.000Z"
updated: "2026-06-09T07:52:20.981Z"
type: "Paper"
topics:
  - "Agents"
  - "Open Source"
subtopics:
  - "Memory"
  - "Agent Frameworks"
upvotes: 1568
source_url: "https://arxiv.org/abs/2606.01528"
comments: 0
truncated: true
---

# MobileLLM's JAMEL Teaches AI Agents to Explore Unfamiliar Apps Without Human Labels

> JAMEL trains GUI agents to explore and remember simultaneously, using JavaScript code coverage as a free training signal — no human labels needed.

Getting a language model agent to genuinely explore an unfamiliar app is harder than it sounds. Ask it to poke around a new e-commerce site and it will often loop through the same three buttons, convinced it has seen everything. The root cause is a chicken-and-egg problem: effective exploration requires memory, and without remembering what has already been tried, an agent can easily repeat exhausted behaviors instead of discovering new states. A new paper from the [MobileLLM group](https://github.com/MobileLLM/JAMEL) tackles this directly with **JAMEL** (Joint Agent Memory and Exploration Learning), an open-source framework that trains memory and exploration together rather than treating them as separate problems.

## The vicious cycle agents are stuck in

Modern LLM agents operating over long sessions face a brutal trade-off. Keeping the full interaction history in context is accurate but burns tokens fast. Compressing that history into a learned latent memory (a compact vector summary the model can query) is efficient, but training that compressor has always been the hard part: what does a "good" memory even look like, and who labels it?

In open-ended environments, agents often struggle to explore effectively, especially when external task rewards are sparse or unavailable. Agent performance degrades when instructions are underspecified and the true entry point is visually inconspicuous, and the key bottleneck is weak proactive exploration after an initial strategy fails. This is not a niche edge case , it is the default condition for any agent deployed on a real app it has never seen before.

## Memory and exploration as a feedback loop

JAMEL's main insight is that memory and exploration form a mutually reinforcing loop: memory helps the agent avoid repeated behaviors and identify unexplored actions, while novelty-driven exploration provides supervision for what the memory should encode. This reframes the labeling problem entirely. Instead of asking humans to annotate what the agent should remember, the system generates its own training signal by measuring how much new ground it covers.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [JAMEL: Joint Agent Memory and Exploration Learning via Novelty Signals (arXiv)](https://arxiv.org/abs/2606.01528)
- [MobileLLM/JAMEL GitHub Repository](https://github.com/MobileLLM/JAMEL)
- [JAMEL-9B Model on Hugging Face](https://huggingface.co/BlitherBoom/JAMEL-9B)
- [MAI-UI Technical Report: Real-World Centric Foundation GUI Agents](https://arxiv.org/html/2512.22047v1)
- [Toward Autonomous UI Exploration: The UIExplorer Benchmark](https://arxiv.org/pdf/2506.17779)
