# VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction arXiv: https://arxiv.org/abs/2610.06293 ยท HTML: https://mlsanity.com/paper/2610.06293/ ## Key facts - No citing papers in the map yet (data through 14 Oct 2026). - Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models. - Builds on 38 of its 93 references that are in the map. - First posted on arXiv 5 Oct 2026. ## Placed in - Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/) - Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/) ## Builds on (most cited first, 30 of 38) - [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) - [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025) - [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024) - [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://mlsanity.com/paper/2503.07536/) (2025) - [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025) - [Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://mlsanity.com/paper/2501.07542/) (2025) - [LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents](https://mlsanity.com/paper/2311.05437/) (2023) - [Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning](https://mlsanity.com/paper/2508.04416/) (2025) - [PyVision: Agentic Vision with Dynamic Tooling](https://mlsanity.com/paper/2507.07998/) (2025) - [PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection](https://mlsanity.com/paper/2502.12119/) (2025) - [DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving](https://mlsanity.com/paper/2512.07745/) (2025) - [Visual Prompting in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2409.15310/) (2024) - [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025) - [Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1](https://mlsanity.com/paper/2503.24376/) (2025) - [From Editor to Dense Geometry Estimator](https://mlsanity.com/paper/2509.04338/) (2025) - [Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning](https://mlsanity.com/paper/2511.12344/) (2025) - [RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs](https://mlsanity.com/paper/2507.03253/) (2025) - [LATTE: Learning to Think with Vision Specialists](https://mlsanity.com/paper/2412.05479/) (2024) - [Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors](https://mlsanity.com/paper/2501.02519/) (2025) - [GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision](https://mlsanity.com/paper/2412.00392/) (2024) - [OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models](https://mlsanity.com/paper/2503.08686/) (2025) - [AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design](https://mlsanity.com/paper/2608.13560/) (2026) - [SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks](https://mlsanity.com/paper/2506.14512/) (2025) - [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://mlsanity.com/paper/2608.03972/) (2026) - [Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Prediction](https://mlsanity.com/paper/2501.05925/) (2025) - [STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2505.22400/) (2025) - [FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning](https://mlsanity.com/paper/2602.22963/) (2026) - [Robotic Manipulation is Vision-to-Geometry Mapping: Vision-Geometry Backbones over Language and Video Models](https://mlsanity.com/paper/2604.12908/) (2026) ## Abstract (arXiv) Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in video understanding, yet their reliance on retrospective summarization and text-centric priors often limits their ability to bridge unobserved causal transitions when applied to Video Event Prediction (VEP). To address this, we propose VepAgent, an agentic framework that integrates causal-transition reasoning with tool-augmented reinforcement learning (RL) for robust VEP. Unlike prior methods that passively project future trajectories from historical dependencies, our approach explicitly models the logical progression from terminal observed states to future events. Specifically, we first construct futurebench-4K, a high-quality chain-of-thought dataset for supervised fine-tuning (SFT) that effectively bridges the causal-logic gap by structuring the deduction of unobserved intermediate states. Subsequently, we develop a diagnostic tool library integrating state tracking, frame retrieval, and region magnification, enabling the agent to dynamically augment reasoning with external tools to recover missing spatio-temporal evidence and resolve visual ambiguities during inference. Moreover, we propose a composite reward mechanism that jointly optimizes prediction accuracy, causal coherence, and reliable prior, compelling the agent to rely on genuine visual grounding rather than superficial textual similarities. Extensive evaluations on FutureBench and NEPBench datasets demonstrate that our method achieves state-of-the-art performance, significantly outperforming larger MLLMs and validating the empirical effectiveness of our agentic, future-oriented reasoning paradigm.