Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
cs.LG, cs.AI, cs.CL
Submitted: 2026-10-03
Updated: 2026-10-06
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
- The Llama 3 Herd of Models
- VisPlay: Self-Evolving Vision-Language Models from Images
- R-Zero: Self-Evolving Reasoning LLM from Zero Data
- G-Zero: Self-Play for Open-Ended Generation from Zero Data
- Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
- Qwen2.5-Coder Technical Report
- Verifier-Backed Hard Problem Generation for Mathematical Reasoning
- MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
- MathDebugger: Detecting and Diagnosing Errors in Synthetic Mathematical Data
- SPICE: Self-Play In Corpus Environments Improves Reasoning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
- Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
- A Survey on Self-Evolution of Large Language Models
- OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks