🚀NEW COURSEVibe Coding AI Apps with Claude Code 🤖✨Enroll now
← All papers  /  May 11, 2026
Agents

Continual Harness: Online Adaptation for Self-Improving Foundation Agents

First page
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
The curator’s take

The last step before online learning. Continual Harness keeps history, memory, skills, prompts, and sub-agent specs across trajectories and mutates them while the agent runs, then goes further and updates the weights DAgger-style from what just happened. The presenter calls test-time training the direction that matters most.

Ask this paper

Key points
01

CRUD over the whole harness state during execution, not between runs.

02

Online loss and process rewards drive adaptation mid-trajectory, including weight updates.

Abstract

Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-observability decision-making. We first report our Gemini Plays Pokemon (GPP) experiments. With iterative human-in-the-loop harness refinement, GPP became the first AI system to complete Pokemon Blue, Yellow Legacy on hard mode, and Crystal without a lost battle. In the hardest stages, the agent itself began iterating on its strategy through long-context memory, surfacing emergent self-improvement signals alongside human-in-the-loop refinement. Continual Harness removes the human fully from this loop: a reset-free self-improving harness for embodied agents that formalizes and automates what we observed. Starting from only a minimal environment interface, the agent alternates between acting and refining its own prompt, sub-agents, skills, and memory, drawing on any past trajectory data. Prompt-optimization methods require episode resets; Continual Harness adapts online within a single run. On Pokemon Red and Emerald across frontier models, Continual Harness starting from scratch substantially reduces button-press cost relative to the minimalist baseline and recovers a majority of the gap to a hand-engineered expert harness, with capability-dependent gains, despite starting from the same raw interface with no curated knowledge, no hand-crafted tools, and no domain scaffolding. We then close the loop with the model itself: an online process-reward co-learning loop, in which an open-source agent's rollouts through the refining harness are relabeled by a frontier teacher and used to update the model, drives sustained in-game milestone progress on Pokemon Red without resetting the environment between training iterations.

Every Monday
Get next week’s papers.
Subscribe on Substack