# Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining arXiv: https://arxiv.org/abs/2603.01465 · HTML: https://mlsanity.com/paper/2603.01465/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models. - Builds on 26 of its 30 references that are in the map. - First posted on arXiv 2 Mar 2026. ## Placed in - Vision-language-action models / [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/) ## Builds on (most cited first, 26 of 26) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022) - [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023) - [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024) - [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015) - [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023) - [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024) - [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017) - [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024) - [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023) - [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023) - [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025) - [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019) - [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021) - [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023) - [ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills](https://mlsanity.com/paper/2302.04659/) (2023) - [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024) - [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025) - [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025) - [Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward](https://mlsanity.com/paper/1801.00054/) (2017) - [Frame-Voyager: Learning to Query Frames for Video Large Language Models](https://mlsanity.com/paper/2410.03226/) (2024) - [MemER: Scaling Up Memory for Robot Control via Experience Retrieval](https://mlsanity.com/paper/2510.20328/) (2025) - [SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation](https://mlsanity.com/paper/2501.18564/) (2025) - [HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy](https://mlsanity.com/paper/2510.00695/) (2025) - [ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context](https://mlsanity.com/paper/2510.04246/) (2025) - [HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models](https://mlsanity.com/paper/2512.09928/) (2025) ## Built on by (most cited first, 8 of 8) - [μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models](https://mlsanity.com/paper/2606.12497/) (2026) - [KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies](https://mlsanity.com/paper/2606.23589/) (2026) - [WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot Manipulation](https://mlsanity.com/paper/2606.17463/) (2026) - [ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation](https://mlsanity.com/paper/2608.02326/) (2026) - [UniMPA: A Unified Memory-Prediction-Action Model via Action-Grounded Transition Modeling](https://mlsanity.com/paper/2609.11875/) (2026) - [Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models](https://mlsanity.com/paper/2609.03927/) (2026) - [EvoMem-VLA: State-Evolution Memory for Long-Horizon Robot Manipulation](https://mlsanity.com/paper/2610.05418/) (2026) - [Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning](https://mlsanity.com/paper/2610.10857/) (2026) ## Abstract (arXiv) Existing Vision-Language-Action (VLA) models often struggle to generalize to long-horizon tasks due to their heavy reliance on immediate observations. While recent studies incorporate retrieval mechanisms or extend context windows to handle procedural tasks, they often struggle to capture Non-Markovian dependencies, where optimal actions rely solely on specific past states rather than the current observation. To address this, we introduce Keyframe-Chaining VLA, a framework that extracts and links key historical frames to model long-horizon dependencies. Specifically, we propose an automatic keyframe selector that learns a discriminative embedding space, effectively identifying distinct state transitions. To capture task-critical information, we design a progress-aware query mechanism that dynamically retrieves historical frames based on their temporal relevance to the current execution phase. These selected keyframes are integrated into the VLA as interleaved visual tokens, explicitly grounding the policy in the long-horizon temporal context. Finally, we introduce a suite of four Non-Markovian manipulation tasks built upon the ManiSkill simulator to measure task success rates. Experimental results demonstrate that our method achieves superior performance, effectively tackling robot manipulation tasks characterized by long-horizon temporal dependencies. Code is available at https://github.com/cytoplastm/KC-VLA.