Agentic-TTT: Training test-time policy for test-time training
cs.LG, cs.AI, cs.CL
Submitted: 2026-10-08
Updated: 2026-10-08
Terminology
Sources
- Self-Improving LLM Agents at Test-Time
- Program Synthesis with Large Language Models
- On the Measure of Intelligence
- Effective LoRA Adapter Routing using Task Representations
- The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
- Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
- Qwen2.5-Coder Technical Report
- Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
- MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts
- ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism
- Progressive Neural Networks
- Adaptive Minds: Empowering Agents with LoRA-as-Tools
- End-to-End Test-Time Training for Long Context
- A Lightweight Framework for Trigger-Guided LoRA-Based Self-Adaptation in LLMs
- Learning to Discover at Test Time
- Test-Time Training Done Right
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks