# Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards

arXiv: https://arxiv.org/abs/2603.09117 · HTML: https://mlsanity.com/paper/2603.09117/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 29 of 29)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions](https://mlsanity.com/paper/2506.09038/) (2025)
- [Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty](https://mlsanity.com/paper/2507.16806/) (2025)
- [Taming Overconfidence in LLMs: Reward Calibration in RLHF](https://mlsanity.com/paper/2410.09724/) (2024)
- [SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales](https://mlsanity.com/paper/2405.20974/) (2024)
- [On Verbalized Confidence Scores for LLMs](https://mlsanity.com/paper/2412.14737/) (2024)
- [Reasoning Models Better Express Their Confidence](https://mlsanity.com/paper/2505.14489/) (2025)
- [Are Reasoning Models More Prone to Hallucination?](https://mlsanity.com/paper/2505.23646/) (2025)
- [Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models](https://mlsanity.com/paper/2506.06395/) (2025)
- [Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models](https://mlsanity.com/paper/2502.11028/) (2025)
- [Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs](https://mlsanity.com/paper/2402.10612/) (2024)
- [Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception](https://mlsanity.com/paper/2502.11677/) (2025)
- [Do LLMs estimate uncertainty well in instruction-following?](https://mlsanity.com/paper/2410.14582/) (2024)
- [SConU: Selective Conformal Uncertainty in Large Language Models](https://mlsanity.com/paper/2504.14154/) (2025)
- [Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes](https://mlsanity.com/paper/2508.11800/) (2025)
- [C2GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning](https://mlsanity.com/paper/2509.23129/) (2025)
- [Towards Harmonized Uncertainty Estimation for Large Language Models](https://mlsanity.com/paper/2505.19073/) (2025)

## Built on by (most cited first, 14 of 14)

- [Process Supervision of Confidence Margin for Calibrated LLM Reasoning](https://mlsanity.com/paper/2604.23333/) (2026)
- [Verifiable Rewards for Calibrated Probabilistic Forecasting](https://mlsanity.com/paper/2607.00164/) (2026)
- [What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness](https://mlsanity.com/paper/2607.08046/) (2026)
- [CALIBER: Calibrating Confidence Before and After Reasoning in Language Models](https://mlsanity.com/paper/2606.24281/) (2026)
- [From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents](https://mlsanity.com/paper/2608.16002/) (2026)
- [Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models](https://mlsanity.com/paper/2609.06419/) (2026)
- [Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format](https://mlsanity.com/paper/2609.09882/) (2026)
- [On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models](https://mlsanity.com/paper/2609.32470/) (2026)
- [Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models](https://mlsanity.com/paper/2609.33290/) (2026)
- [Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs](https://mlsanity.com/paper/2609.33721/) (2026)
- [When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation](https://mlsanity.com/paper/2609.34454/) (2026)
- [Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts](https://mlsanity.com/paper/2609.34857/) (2026)
- [OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One](https://mlsanity.com/paper/2610.00381/) (2026)
- [Test-time Calibration Learning for Large Language Model Reasoning](https://mlsanity.com/paper/2610.02695/) (2026)

## Abstract (arXiv)

Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from calibration degeneration, where models become excessively over-confident in incorrect answers. Previous studies devote to directly incorporating calibration objective into existing optimization target. However, our theoretical analysis demonstrates that there exists a fundamental gradient conflict between the optimization for maximizing policy accuracy and minimizing calibration error. Building on this insight, we propose DCPO, a simple yet effective framework that systematically decouples reasoning and calibration objectives. Extensive experiments demonstrate that our DCPO not only preserves accuracy on par with GRPO but also achieves the best calibration performance and substantially mitigates the over-confidence issue. Our study provides valuable insights and practical solution for more reliable LLM deployment.