# Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL

arXiv: https://arxiv.org/abs/2510.08977 · HTML: https://mlsanity.com/paper/2510.08977/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- Synthetic data and self-improvement for LLMs / [Self-play RL for reasoning](https://mlsanity.com/synth/self-play-rl-for-reasoning/)

## Builds on (most cited first, 30 of 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [Learning to Reason without External Rewards](https://mlsanity.com/paper/2505.19590/) (2025)
- [Spurious Rewards: Rethinking Training Signals in RLVR](https://mlsanity.com/paper/2506.10947/) (2025)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [General-Reasoner: Advancing LLM Reasoning Across All Domains](https://mlsanity.com/paper/2505.14652/) (2025)
- [Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization](https://mlsanity.com/paper/2504.05812/) (2025)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models](https://mlsanity.com/paper/2502.17387/) (2025)
- [Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination](https://mlsanity.com/paper/2507.10532/) (2025)
- [Self-rewarding correction for mathematical reasoning](https://mlsanity.com/paper/2502.19613/) (2025)
- [Can Large Reasoning Models Self-Train?](https://mlsanity.com/paper/2505.21444/) (2025)
- [Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models](https://mlsanity.com/paper/2506.06395/) (2025)
- [No Free Lunch: Rethinking Internal Feedback for LLM Reasoning](https://mlsanity.com/paper/2506.17219/) (2025)
- [Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models](https://mlsanity.com/paper/2508.00410/) (2025)
- [Training Language Models to Win Debates with Self-Play Improves Judge Accuracy](https://mlsanity.com/paper/2409.16636/) (2024)

## Built on by (most cited first, 3 of 3)

- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)
- [When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2605.25864/) (2026)
- [Self-Verifier Capture in Unified Visual Generators: Diagnosing and Repairing Closed-Loop Self-Reward](https://mlsanity.com/paper/2610.16500/) (2026)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models (LLMs) but is bottlenecked by scarce labeled data. Reinforcement learning with intrinsic rewards (RLIR) offers a scalable alternative via self-rewarding, yet often suffers from instability and inferior performance. We trace this gap to a systemic bias in confidence-coupled self-rewarding: the model tends to over-reward high-confidence mistakes, forming a self-confirming loop. We quantify this feedback-loop bias with three metrics: reward noise magnitude (rho_noise), policy-reward coupling (rho_selfbias), and over-/under-reward skew (rho_symbias). Our analyses show a compounding effect where strong coupling amplifies confidence-conditioned errors and drives a drift toward over-reward, leading to instability and a lower performance ceiling. To mitigate this, we propose reinforcement learning with ensembled rewards (RLER), which aggregates diverse models with adaptive reward interpolation and disagreement-aware rollout selection to reduce coupling and suppress over-reward drift. Extensive experiments show that RLER improves by 6.2% over the best RLIR baseline and is within 3.6% of RLVR, while exhibiting stable scaling on unlabeled samples.