# Reinforcing Video Reasoning Segmentation to Think Before It Segments

arXiv: https://arxiv.org/abs/2508.11538 · HTML: https://mlsanity.com/paper/2508.11538/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos](https://mlsanity.com/paper/2501.04001/) (2025)
- [Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding](https://mlsanity.com/paper/2503.13377/) (2025)
- [Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives](https://mlsanity.com/paper/2501.04003/) (2025)
- [GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing](https://mlsanity.com/paper/2503.10639/) (2025)
- [UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning](https://mlsanity.com/paper/2505.14231/) (2025)
- [VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning](https://mlsanity.com/paper/2505.12081/) (2025)
- [Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning](https://mlsanity.com/paper/2506.22624/) (2025)
- [Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration](https://mlsanity.com/paper/2505.20256/) (2025)
- [HyperSeg: Towards Universal Visual Segmentation with Large Language Model](https://mlsanity.com/paper/2411.17606/) (2024)
- [InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models](https://mlsanity.com/paper/2412.14006/) (2024)
- [SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2505.22596/) (2025)
- [MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO](https://mlsanity.com/paper/2505.13031/) (2025)
- [PixelThink: Towards Efficient Chain-of-Pixel Reasoning](https://mlsanity.com/paper/2505.23727/) (2025)
- [The Devil is in Temporal Token: High Quality Video Reasoning Segmentation](https://mlsanity.com/paper/2501.08549/) (2025)
- [ViLLa: Video Reasoning Segmentation with Large Language Model](https://mlsanity.com/paper/2407.14500/) (2024)
- [Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning](https://mlsanity.com/paper/2507.00748/) (2025)

## Built on by (most cited first, 15 of 15)

- [VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice](https://mlsanity.com/paper/2601.05175/) (2026)
- [Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models](https://mlsanity.com/paper/2510.05034/) (2025)
- [Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model](https://mlsanity.com/paper/2509.07825/) (2025)
- [Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation](https://mlsanity.com/paper/2510.19592/) (2025)
- [Evidence-Backed Video Question Answering](https://mlsanity.com/paper/2607.11862/) (2026)
- [Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification](https://mlsanity.com/paper/2605.17531/) (2026)
- [AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method](https://mlsanity.com/paper/2604.22836/) (2026)
- [RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation](https://mlsanity.com/paper/2605.07334/) (2026)
- [SteerSeg: Attention Steering for Reasoning Video Segmentation](https://mlsanity.com/paper/2605.14908/) (2026)
- [MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentation](https://mlsanity.com/paper/2605.26621/) (2026)
- [Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought](https://mlsanity.com/paper/2605.27764/) (2026)
- [VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation](https://mlsanity.com/paper/2606.06819/) (2026)
- [FeVOS: Foresight Expression Video Object Segmentation](https://mlsanity.com/paper/2606.25585/) (2026)
- [Event-Aware Instructed Assistant for Referring Video Segmentation](https://mlsanity.com/paper/2606.26994/) (2026)
- [Less from More: Reinforcing Sparse Video Reasoning from Dense References](https://mlsanity.com/paper/2610.10893/) (2026)

## Abstract (arXiv)

Video reasoning segmentation (VRS) endeavors to delineate referred objects in videos guided by implicit instructions that encapsulate human intent and temporal logic. Previous approaches leverage large vision language models (LVLMs) to encode object semantics into <SEG> tokens for mask prediction. However, this paradigm suffers from limited interpretability during inference and suboptimal performance due to inadequate spatiotemporal reasoning. Drawing inspiration from seminal breakthroughs in reinforcement learning, we introduce Veason-R1, a specialized LVLM for VRS that emphasizes structured reasoning in segmentation. Veason-R1 is trained through Group Relative Policy Optimization (GRPO) augmented with Chain-of-Thought (CoT) initialization. To begin with, we curate high-quality CoT training data to instill structured reasoning trajectories, bridging video-level semantics and frame-level spatial grounding, yielding the supervised fine-tuned model Veason-SFT. Subsequently, GRPO fine-tuning encourages efficient exploration of the reasoning space by optimizing reasoning chains. To this end, we incorporate a holistic reward mechanism that synergistically enhances spatial alignment and temporal consistency, bolstering keyframe localization and fine-grained grounding. Comprehensive empirical evaluations demonstrate that Veason-R1 achieves state-of-the-art performance on multiple benchmarks, surpassing prior art by significant margins (e.g., +1.3 J &F in ReVOS and +10.0 J &F in ReasonVOS), while exhibiting robustness to hallucinations (+8.8 R). Our code and model weights will be available at Veason-R1.