Article

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

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.

Part of the event: Tingwen Du et al. propose the SERA self-evolving robotic agent framework

This page provides a summary and source link only.