# CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment

arXiv: https://arxiv.org/abs/2606.14691 · HTML: https://mlsanity.com/paper/2606.14691/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 12 of 12)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models](https://mlsanity.com/paper/2412.07755/) (2024)
- [TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs](https://mlsanity.com/paper/2505.20777/) (2025)
- [HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2603.18683/) (2026)
- [Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models](https://mlsanity.com/paper/2510.10104/) (2025)
- [HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning](https://mlsanity.com/paper/2606.10507/) (2026)
- [VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought](https://mlsanity.com/paper/2604.21396/) (2026)
- [Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention](https://mlsanity.com/paper/2605.22072/) (2026)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) has successfully elicited the reasoning capabilities of large language models, motivating its extension to multimodal scenarios. Existing methods primarily focus on improving the visual coverage of reasoning traces and mitigating visual hallucinations, but underestimate the semantic inconsistency between the reasoning process and the final answer. In this paper, we delve into thinking-answer inconsistency in RLVR for large vision-language models (LVLMs), showing thorough analyses of rollouts collected throughout Group Relative Policy Optimization (GRPO) training process and post-RLVR evaluation outputs that this issue persists during training and remains present during inference. Motivated by the analysis, we propose Consistency-Oriented Reasoning Alignment (CORA), which introduces thinking-answer semantic consistency into RLVR through a lightweight plug-and-play consistency reward model, and further incorporates Hybrid Reward Advantage Splitting (HRAS) to stably coordinate task and consistency optimization. Extensive experiments across representative multimodal reasoning benchmarks and mainstream LVLMs show that CORA improves task performance while effectively mitigating thinking-answer inconsistency, leading to more faithful reasoning traces.