# ICLR: In-Context Imitation Learning with Visual Reasoning

arXiv: https://arxiv.org/abs/2603.07530 · HTML: https://mlsanity.com/paper/2603.07530/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 7 of its 47 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 7 of 7)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer](https://mlsanity.com/paper/2510.03342/) (2025)
- [Gemini Robotics: Bringing AI into the Physical World](https://mlsanity.com/paper/2503.20020/) (2025)
- [A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation](https://mlsanity.com/paper/2602.01067/) (2026)
- [Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control](https://mlsanity.com/paper/2602.13193/) (2026)

## Built on by (most cited first, 4 of 4)

- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [SynthICL: Scalable In-context Imitation Learning with Synthetic Data](https://mlsanity.com/paper/2606.08154/) (2026)
- [Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning](https://mlsanity.com/paper/2609.10177/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)

## Abstract (arXiv)

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit representations of task intent. This limitation hinders performance in complex and ambiguous task settings where the same actions may be consistent with different objectives. To address this, we present In-Context Imitation Learning with Visual Reasoning (ICLR), a novel framework that augments demonstration prompts with structured visual reasoning traces representing anticipated future robot trajectories in image space. ICLR also jointly learns to generate reasoning traces and low-level actions within a unified autoregressive transformer, enabling the model to mimic not only action prediction but also the reasoning process that leads to those actions. We extensively evaluate ICLR in both simulation and real-world manipulation tasks and demonstrate consistent improvements in success rates and generalization to unseen tasks and novel object configurations compared to other in-context imitation learning methods. These results suggest that incorporating embodied visual reasoning represents a promising direction for enhancing the robustness and generalization of robotic in-context learning systems.