VISTA: Active Exploration for Self-Improvement in Embodied Agents

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Agentic embodied intelligence plays a foundational role in open-ended, dynamic physical environments. Rather than treating policy learning as an end-to-end mapping from instructions to actions, recent studies reveal that embodied systems depend not only on pre-trained foundation models, but also on harness. Prior approaches largely treat rollouts as static logs for post-hoc reflection, producing harness updates without autonomously testing and refining them through subsequent embodied interaction. To address this challenge, we propose VISTA, a meta-agent framework that transforms post-hoc rollout reflection into active self-exploration for embodied harness improvement. Specifically, VISTA maintains a harness graph that records the lineage of proposed harnesses, which enables the meta-agent to retrieve prior hypotheses, build on effective mechanisms, and avoid repeatedly exploring failed directions. Each iteration begins from a retained harness version and its execution evidence. Rather than directly committing an update from these historical trajectories, the meta-agent actively explores in the environment. It autonomously generates new rollouts, probes execution failures and recovery behaviors, and iteratively modifies the harness based on the resulting evidence. The refined harness is then evaluated afresh and added to the harness graph. We evaluate VISTA on the LIBERO-Pro, RoboCasa, and RoboTwin benchmarks. Experimental results demonstrate that VISTA progressively improves task success and is more rollout-efficient than static reflection, achieving higher success rates with fewer simulator rollouts.

• Zetta $ζ$: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

  arXiv (Cornell University) 2026 · 0 citations

• RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents

  arXiv (Cornell University) 2026 · 0 citations

• Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents

  arXiv (Cornell University) 2026 · 0 citations

• EMHO: EMbodied Agent Harness Optimization via Experience Traces

  arXiv (Cornell University) 2026 · 0 citations

• Recursive Self Improvement for Embodied Agents—A Survey of Foundations Mechanisms Harnesses and Evaluation

  Preprints.org 2026 · 0 citations