# TTCS: Test-Time Curriculum Synthesis for Self-Evolving

arXiv: https://arxiv.org/abs/2601.22628 · HTML: https://mlsanity.com/paper/2601.22628/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Synthetic data and self-improvement for LLMs / [Synthetic reasoning data and bootstrapping](https://mlsanity.com/synth/synthetic-reasoning-data-and-bootstrapping/)

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

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [The Surprising Effectiveness of Test-Time Training for Few-Shot Learning](https://mlsanity.com/paper/2411.07279/) (2024)
- [SPICE: Self-Play In Corpus Environments Improves Reasoning](https://mlsanity.com/paper/2510.24684/) (2025)
- [Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop](https://mlsanity.com/paper/2311.16822/) (2023)
- [SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data](https://mlsanity.com/paper/2505.20347/) (2025)
- [The Majority is not always right: RL training for solution aggregation](https://mlsanity.com/paper/2509.06870/) (2025)
- [VisPlay: Self-Evolving Vision-Language Models from Images](https://mlsanity.com/paper/2511.15661/) (2025)
- [Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation](https://mlsanity.com/paper/2502.14948/) (2025)
- [Guided Self-Evolving LLMs with Minimal Human Supervision](https://mlsanity.com/paper/2512.02472/) (2025)
- [First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training](https://mlsanity.com/paper/2505.22453/) (2025)
- [Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains](https://mlsanity.com/paper/2504.20199/) (2025)
- [ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model](https://mlsanity.com/paper/2510.24285/) (2025)

## Built on by (most cited first, 19 of 19)

- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [SPADE: Self-Play in Adaptive Synthetic Executable Environments](https://mlsanity.com/paper/2608.19197/) (2026)
- [Scaling Self-Play with Self-Guidance](https://mlsanity.com/paper/2604.20209/) (2026)
- [Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting](https://mlsanity.com/paper/2605.19444/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?](https://mlsanity.com/paper/2608.00155/) (2026)
- [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026)
- [A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference](https://mlsanity.com/paper/2609.01679/) (2026)
- [TTSR: Test-Time Self-Evolving via Reflection](https://mlsanity.com/paper/2603.03297/) (2026)
- [SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning](https://mlsanity.com/paper/2607.26873/) (2026)
- [The Power of Test-Time Training for Approximate Sampling](https://mlsanity.com/paper/2606.11437/) (2026)
- [ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction](https://mlsanity.com/paper/2608.20920/) (2026)
- [Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics](https://mlsanity.com/paper/2608.17268/) (2026)
- [Unsupervised Post-Training of Foundation Models: A Survey](https://mlsanity.com/paper/2608.24982/) (2026)
- [Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA](https://mlsanity.com/paper/2609.16660/) (2026)
- [STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution](https://mlsanity.com/paper/2609.18642/) (2026)
- [BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification](https://mlsanity.com/paper/2609.34785/) (2026)
- [Questioning the Questions: Sustaining Self-Evolution in Reasoning Models](https://mlsanity.com/paper/2610.04299/) (2026)
- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)

## Abstract (arXiv)

Test-Time Training offers a promising way to improve the reasoning ability of large language models (LLMs) by adapting the model using only the test questions. However, existing methods struggle with difficult reasoning problems for two reasons: raw test questions are often too difficult to yield high-quality pseudo-labels, and the limited size of test sets makes continuous online updates prone to instability. To address these limitations, we propose TTCS, a co-evolving test-time training framework. Specifically, TTCS initializes two policies from the same pretrained model: a question synthesizer and a reasoning solver. These policies evolve through iterative optimization: the synthesizer generates progressively challenging question variants conditioned on the test questions, creating a structured curriculum tailored to the solver's current capability, while the solver updates itself using self-consistency rewards computed from multiple sampled responses on both original test and synthetic questions. Crucially, the solver's feedback guides the synthesizer to generate questions aligned with the model's current capability, and the generated question variants in turn stabilize the solver's test-time training. Experiments show that TTCS consistently strengthens the reasoning ability on challenging mathematical benchmarks and transfers to general-domain tasks across different LLM backbones, highlighting a scalable path towards dynamically constructing test-time curricula for self-evolving. Our code and implementation details are available at https://github.com/XMUDeepLIT/TTCS.