# Self-rewarding alignment and self-training

Area: [Synthetic data and self-improvement for LLMs](https://mlsanity.com/synth/index.md). HTML: https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/

## Key facts

- Self-rewarding alignment and self-training: 189 papers on arXiv since 2023 (data through 14 Oct 2026).
- 39 of its 189 mapped papers (21%) cite “Self-Rewarding Language Models” (2024, arXiv 2401.10020).
- 32 of its 189 mapped papers (17%) cite “Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models” (2024, arXiv 2401.01335).
- 18 new papers 17 Sep–14 Oct.

## Most cited here

- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024), cited by 39 papers here
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024), cited by 32 papers here
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023), cited by 21 papers here
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024), cited by 19 papers here
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024), cited by 14 papers here
- [Self-Improvement in Language Models: The Sharpening Mechanism](https://mlsanity.com/paper/2412.01951/) (2024), cited by 14 papers here
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024), cited by 13 papers here
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023), cited by 10 papers here
- [Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences](https://mlsanity.com/paper/2404.03715/) (2024), cited by 10 papers here
- [Recursive Introspection: Teaching Language Model Agents How to Self-Improve](https://mlsanity.com/paper/2407.18219/) (2024), cited by 9 papers here

## New (17 Sep–14 Oct)

- [Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization](https://mlsanity.com/paper/2610.12855/) (2026-10-09)
- [EliteTable: Self-Improving Program Search for Executable Control Policies](https://mlsanity.com/paper/2610.12536/) (2026-10-08)
- [MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement](https://mlsanity.com/paper/2610.11959/) (2026-10-08)
- [Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models](https://mlsanity.com/paper/2610.10623/) (2026-10-07)
- [The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules](https://mlsanity.com/paper/2610.09239/) (2026-10-07)
- [ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement](https://mlsanity.com/paper/2610.06347/) (2026-10-05)
- [When Is Enough Enough in Self-Evolving LLM Systems?](https://mlsanity.com/paper/2610.04756/) (2026-10-03)
- [PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time](https://mlsanity.com/paper/2610.02885/) (2026-10-02)
- [Train Ahead, Distill Back: Bootstrapping On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2609.37132/) (2026-09-29)
- [Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-Policyness](https://mlsanity.com/paper/2609.36945/) (2026-09-29)
- [Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving](https://mlsanity.com/paper/2609.36750/) (2026-09-29)
- [PADMÉ: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators](https://mlsanity.com/paper/2609.36086/) (2026-09-28)
- [Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training](https://mlsanity.com/paper/2609.34279/) (2026-09-28)
- [COEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement](https://mlsanity.com/paper/2609.33398/) (2026-09-27)
- [SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought](https://mlsanity.com/paper/2609.33181/) (2026-09-27)
- [StraTune: Adaptive Selection of Revision Operators for Self-Evolving LLM Skills](https://mlsanity.com/paper/2609.32886/) (2026-09-26)
- [Strategically Diverse Sampling for Self-Training](https://mlsanity.com/paper/2609.31571/) (2026-09-25)
- [EvoAudio: Recursive Self-Improvement for Audio Understanding](https://mlsanity.com/paper/2609.27389/) (2026-09-23)