# Agentic-TTT: Training test-time policy for test-time training

arXiv: https://arxiv.org/abs/2610.12002 · HTML: https://mlsanity.com/paper/2610.12002/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 64 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM agents and tool use

## Builds on (most cited first, 17 of 17)

- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts](https://mlsanity.com/paper/2404.15159/) (2024)
- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [Test-Time Training Done Right](https://mlsanity.com/paper/2505.23884/) (2025)
- [Learning to Discover at Test Time](https://mlsanity.com/paper/2601.16175/) (2026)
- [End-to-End Test-Time Training for Long Context](https://mlsanity.com/paper/2512.23675/) (2025)
- [ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism](https://mlsanity.com/paper/2508.11356/) (2025)
- [Self-Improving LLM Agents at Test-Time](https://mlsanity.com/paper/2510.07841/) (2025)
- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning](https://mlsanity.com/paper/2510.04786/) (2025)
- [Effective LoRA Adapter Routing using Task Representations](https://mlsanity.com/paper/2601.21795/) (2026)
- [Adaptive Minds: Empowering Agents with LoRA-as-Tools](https://mlsanity.com/paper/2510.15416/) (2025)
- [Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution](https://mlsanity.com/paper/2601.20379/) (2026)
- [A Lightweight Framework for Trigger-Guided LoRA-Based Self-Adaptation in LLMs](https://mlsanity.com/paper/2509.05385/) (2025)

## Built on by (most cited first, 1 of 1)

- [MMLA-RSI: Recursive Self-Improvement through RTT and RTMA](https://mlsanity.com/paper/2610.20294/) (2026)

## Abstract (arXiv)

Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO competitions or designated open problems. By turning deployment experience into parameter updates, TTT provides a direct mechanism for model-level self-improvement. Yet TTT is not universally beneficial: each TTT algorithm works in different settings, and applying an ill-suited method could waste test-time compute or even damage model performance. Therefore, such parameter-level self-improvement requires agency: the model must decide when TTT is warranted, which algorithm to invoke, and whether an existing skill can be reused. To fill this gap, we introduce Agentic-TTT, which learns a test-time policy to govern those decisions. Agentic-TTT turns TTT procedures into callable tools, treats accumulated skills as an evolving deployment environment, and trains its policy using the observed utility gains from its decisions. On our benchmark, Agentic-TTT nearly doubles the utility over the backbone model, learns to trade off utility against compute, and generalizes to domains unseen during training. Together, these results point toward autonomous self-improvement: models that can decide how to learn from their own deployment experience.