# From Local Corrections to Generalized Skills: Improving Neuro-Symbolic Policies with MEMO

Source: [From Local Corrections to Generalized Skills: Improving Neuro-Symbolic Policies with MEMO](<https://www.sota2.com/research/paper/69aa5f602d603e6de3e4168d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-25T05:00:34.132Z

Authors: Benjamin A. Christie, Yinlong Dai, Mohammad Bararjanianbahnamiri, Simon Stepputtis, Dylan P. Losey

Published: 2026-03-04T19:44:55.000Z

## Abstract

Recent works use a neuro-symbolic framework for general manipulation policies. The advantage of this framework is that -- by applying off-the-shelf vision and language models -- the robot can break complex tasks down into semantic subtasks. However, the fundamental bottleneck is that the robot needs skills to ground these subtasks into embodied motions. Skills can take many forms (e.g., trajectory snippets, motion primitives, coded functions), but regardless of their form skills act as a constraint. The high-level policy can only ground its language reasoning through the available skills; if the robot cannot generate the right skill for the current task, its policy will fail. We propose to address this limitation -- and dynamically expand the robot's skills -- by leveraging user feedback. When a robot fails, humans can intuitively explain what went wrong (e.g., \`\`no, go higher''). While a simple approach is to recall this exact text the next time the robot faces a similar situation, we hypothesize that by collecting, clustering, and re-phrasing natural language corrections across multiple users and tasks, we can synthesize more general text guidance and coded skill templates. Applying this hypothesis we develop Memory Enhanced Manipulation (MEMO). MEMO builds and maintains a retrieval-augmented skillbook gathered from human feedback and task successes. At run time, MEMO retrieves relevant text and code from this skillbook, enabling the robot's policy to generate new skills while reasoning over multi-task human feedback. Our experiments demonstrate that using MEMO to aggregate local feedback into general skill templates enables generalization to novel tasks where existing baselines fall short. See supplemental material here: https://collab.me.vt.edu/memo

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Close the bottle on Real-world tasks](<https://www.sota2.com/research/sota/close-the-bottle-on-real-world-tasks.md>): Close the bottle; Real-world tasks; Success Rate: 100.

- [Empty the cabinet on Real-world tasks](<https://www.sota2.com/research/sota/empty-the-cabinet-on-real-world-tasks.md>): Empty the cabinet; Real-world tasks; Success Rate: 80.

- [Placement of Apple on Table on Real-world tasks](<https://www.sota2.com/research/sota/placement-of-apple-on-table-on-real-world-tasks.md>): Place the apple on the table; Real-world tasks; Success Percentage: 100.

- [Pour the can on Real-world tasks](<https://www.sota2.com/research/sota/pour-the-can-on-real-world-tasks.md>): Pour the can; Real-world tasks; Success Rate: 100.

- [Putting Food in Oven on Real-world tasks](<https://www.sota2.com/research/sota/putting-food-in-oven-on-real-world-tasks.md>): Put the food in the oven; Real-world tasks; Success Rate: 60.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.04560>)

[PDF](<https://arxiv.org/pdf/2603.04560.pdf>)