# Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation

arXiv: https://arxiv.org/abs/2605.00438 · HTML: https://mlsanity.com/paper/2605.00438/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 1 May 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Show-o2: Improved Native Unified Multimodal Models](https://mlsanity.com/paper/2506.15564/) (2025)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [Open-World Object Manipulation using Pre-trained Vision-Language Models](https://mlsanity.com/paper/2303.00905/) (2023)
- [Unified Vision-Language-Action Model](https://mlsanity.com/paper/2506.19850/) (2025)
- [OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning](https://mlsanity.com/paper/2505.11917/) (2025)
- [VLA-0: Building State-of-the-Art VLAs with Zero Modification](https://mlsanity.com/paper/2510.13054/) (2025)
- [Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process](https://mlsanity.com/paper/2511.01718/) (2025)
- [EO-1: An Open Unified Embodied Foundation Model for General Robot Control](https://mlsanity.com/paper/2508.21112/) (2025)
- [dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought](https://mlsanity.com/paper/2509.25681/) (2025)

## Built on by (most cited first, 2 of 2)

- [FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation](https://mlsanity.com/paper/2606.30367/) (2026)
- [Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization](https://mlsanity.com/paper/2608.29880/) (2026)

## Abstract (arXiv)

Long-horizon robotic manipulation requires plans that are both logically coherent and geometrically grounded. Existing Vision-Language-Action policies usually hide planning in latent states or expose only one modality: text-only chain-of-thought encodes causal order but misses spatial constraints, while visual prediction provides geometric cues but often remains local and semantically underconstrained. We introduce Interleaved Vision--Language Reasoning (IVLR), a policy framework built around trace, an explicit intermediate representation that alternates textual subgoals with visual keyframes over the full task horizon. At test time, a single native multimodal transformer self-generates this global semantic-geometric trace from the initial observation and instruction, caches it, and conditions a closed-loop action decoder on the trace, original instruction, and current observation. Because standard robot datasets lack such traces, we construct pseudo-supervision by temporally segmenting demonstrations and captioning each stage with a vision-language model. Across simulated benchmarks for long-horizon manipulation and visual distribution shift, method reaches 95.5% average success on LIBERO, including 92.4% on LIBERO-Long, and 59.4% overall success on SimplerEnv-WidowX. Ablations show that both modalities are necessary: without traces, LIBERO-Long success drops to 37.7%; text-only and vision-only traces reach 62.0% and 68.4%, while the full interleaved trace reaches 92.4%. Stress tests with execution perturbations and masked trace content show moderate degradation, suggesting that the trace can tolerate local corruption and moderate execution drift, but remains limited under stale or incorrect global plans.