# SERA: A Self-Evolving Robotic Agent Framework for History-Dependent Manipulation

- Source: HuggingFace Daily Papers
- Published: 2026-10-21T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/k6m7lmnajfyfjx8obp4wu4pqi
- Original: https://huggingface.co/papers/2610.29560

## Summary

The study proposes SERA (Self-Evolving Robotic Agent), which organizes a high-level VLM into a robotic agent through an editable harness, with a fixed VLA executor providing low-level control. The harness uses observations and execution feedback to maintain task context, and the self-evolution mechanism proposes and evaluates harness revisions through environment rollouts, with the selected configuration fixed before held-out testing. On RoboMME, SERA autonomously selects a configuration reaching 51.38% overall success rate, versus 44.38% without self-evolution.
