arXiv AI
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 27
TTSR: Test-Time Self-Evolving via Reflection
TTSR (Test-Time Self-Reflection) is a framework that enables large language models to adapt during inference by alternating between a Student role that solves test questions and a Teacher role that analyzes failures and generates targeted variant questions. The method incorporates a weakness memory and a strategy note to guide exploration, reducing reliance on noisy pseudo-labels and inefficient rollouts. Experiments on mathematical reasoning benchmarks demonstrate consistent test-time improvements, strong cross-backbone generalization, and transfer to general-domain reasoning tasks.
arXiv Machine Learning
Aug 4
Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics
arXiv:2608. 01522v1 Announce Type: new Abstract: Teaching a language model a skill it has not mastered is obstructed by three recurring difficulties: training data is scarce, ground-truth reasoning traces are usually unavailable, and models often exhibit an apparent ceiling beyond which additional data yields no further improvement.
arXiv AI
Aug 10
Ask-E: An Environment for Calibrated Question Generation
arXiv:2608. 06933v1 Announce Type: cross Abstract: Today, we improve models by training and evaluating them on problems at the frontier of their abilities.
arXiv Machine Learning
Oct 8
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
arXiv:2610.04299v2 Announce Type: replace Abstract: Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper...
arXiv Machine Learning
Jul 9
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
arXiv:2607. 06974v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation.
arXiv AI
Jun 9
CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning
arXiv:2509. 25004v2 Announce Type: replace Abstract: Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still optimize reasoning trajectories over the static problem set, wasting rollout budget on solved or overly difficult problems.