cs.LGNov 17, 2026

Similar Is Not Useful: Selecting In-Context Demonstrations by Closed-Loop Utility

Authors: Jiachen Li, Zhigen Zhao, Shihao Li, Dongmei Chen, Long Chen, Zhuo Xu

Organizations: University of Texas at Austin · Georgia Institute of Technology · General Intelligent Machines, Inc

Abstract

Retrieval-augmented vision-language-action (VLA) policies fill their context with the demonstrations whose frames look most like the current observation under frozen DINOv2 embeddings. We ask whether visual similarity selects the demonstrations that make the policy succeed. For a frozen retrieval-augmented VLA (RICL on π0π_0-FAST, LIBERO), we make the demonstration pool swappable at run time and score each demonstration's utility by regressing the closed-loop success of 60 fixed-size pools on their membership. On initial states disjoint from those used for scoring, pools of the five highest-utility demonstrations succeed on 66.4% of 760 paired episodes across 19 tasks, pools of the five most similar on 55.7%, and random pools on 55.5%. Utility beats similarity by 10.8 points (p=3.2×10−6p=3.2\times10^{-6}; positive on 15 of 18 untied tasks), including on 12 tasks the policy was never primed on, and similarity-selected pools do no better than random (+0.1+0.1 points). Within a task, a pool's visual similarity to the test scenes tracks its success at Spearman 0.10; across tasks, similarity separates tasks whose scenes differ and falls to chance when two tasks share a scene. The gain comes from on-task closed-loop evidence: best-of-ten direct search over pools recovers two-thirds of it with 100 rollouts. Against the shipped 20-demonstration pool, utility-curated pools of five lead by 7.0 points over 560 paired episodes from two evaluation runs (p=0.006p=0.006), and utility-ordered retrieval inside the full pool leads by 4.5 points (p=0.055p=0.055).

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 4, 2026

When Does Retrieval Help? A Study of In-Context Adaptation in Vision-Language-Action Models

Vision-language-action (VLA) models have shown strong potential as generalist robot policies, but adapting them to unseen tasks often requires costly parameter updates. Recent work such as RICL introduces in-context adaptability by retrieving expert demonstrations based on the current VLA observation and providing them as additional context at test time. The effectiveness of this adaptation therefore depends critically on the retrieval mechanism. In this work, we systematically study how different retrieval methods affect both retrieval quality and task performance within the RICL framework. Specifically, we compare four different methods: image-based retrieval, retrieval augmented with VLA's state, retrieval using features from the VLA backbone, and random retrieval. Our experiments yield three main findings. First, no retrieval method consistently dominates the others in task success, while surprisingly, random retrieval achieves a non-trivial success rate. Second, standard retrieval-quality diagnostics do not reliably reflect downstream VLA performance. Third, demonstrations from different but related tasks can provide useful transferable information. Together, these results provide an initial step toward understanding how retrieval mechanisms shape the in-context learning capability of VLA models and their downstream task performance, while highlighting the need for more careful design and evaluation of retrieval mechanisms for reliable test-time adaptation.
Nov 9, 2026

How Much of Your VLA Is kNN

Vision-language-action (VLA) models now exceed 95% success on the LIBERO simulation benchmark, yet it remains unclear how much of this performance requires generalization beyond the training demonstrations. In this work, we show that retrieving nearby demonstrations and reusing their action chunks achieves a success rate of 91.7 % on LIBERO without policy training. Under LIBERO-Plus perturbations, retrieval shows the smallest drop of all evaluated policies. Across nine publicly available VLAs, fine-tuning mostly makes the vision-language backbone a better retrieval key, and the actions of the VLAs remain close to the demonstrations. In addition, we introduce Local Action Consistency (LAC), an offline metric that measures whether nearby observations in representation space are also associated with similar future actions. We show that LAC tracks the success rate of retrieval and can guide the training of a retrieval key. Our evaluation and source code are available at https://github.com/sereact/lerobot_knn.
Jun 14, 2026

Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time

Extending a vision-language-action (VLA) policy to a new task typically requires task-specific teleoperated demonstrations and per-task fine-tuning, making adaptation costly in both data collection and compute. In this paper, we show that this target-side per-task adaptation cost can be replaced by retrieval. Our retrieval-augmented policy is trained once on paired demonstrations from the target embodiment (query) and a cheaper embodiment (pool, e.g., human-hand video), then frozen. New tasks are added at deployment by appending pool-side demonstrations to a retrieval pool. The frozen policy conditions on retrieved trajectories at every control step, so new tasks are absorbed by indexing data rather than updating parameters. Fine-tuning is needed only to take on a new, unseen embodiment, not for each new task. We show that retrieval improves policies beyond a specific backbone, including standard VLA policies, but its effect is especially pronounced in Cosmos Policy, a video-generation-based world-action model (WAM). In this setting, retrieval supplies coarse task progression, while the WAM's future-image objective provides an additional visual consistency signal that strengthens the retrieval-conditioned actions. On PushT, we study how retrieval provides a reusable high-level motion prior for cross-embodiment generalization to unseen goal angles, while on RoboTwin 2.0 our method outperforms cross-embodiment baselines on unseen tasks, and we additionally demonstrate the method on a real robot.