Event
Tingwen Du et al. propose the SERA self-evolving robotic agent framework
2 reports · 2 sources
Tingwen Du and other researchers propose the SERA (Self-Evolving Robotic Agent) framework, which uses a high-level VLM as a planner with an editable harness, paired with a fixed VLA executor for low-level control, to handle non-Markovian (history-dependent) tasks in long-horizon manipulation. 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 the RoboMME benchmark, when SERA autonomously selects configurations, the overall success rate is 51.38%, compared with 44.38% without self-evolution.
Report timeline
- SERA: A Self-Evolving Robotic Agent Framework for History-Dependent Manipulation
The paper proposes SERA (Self-Evolving Robotic Agent), which organizes a high-level VLM as a robotic agent with an editable harness, paired with a fixed VLA executor for low-level control, to handle non-Markovian dependencies in long-horizon manipulation.
arXiv cs.RO ·
- 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.
HuggingFace Daily Papers ·