From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation
What this work does
SERA organizes a high-level vision-language planner around a fixed robot executor. Its harness maintains task context within episodes and is revised between development attempts to improve progress assessment, planning guidance, and recovery.
THE RESEARCH CONVERSATION
Discussion & reactions
Share a question, an insight, or a replication experience. Sign in with GitHub to join the conversation.