Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

Hugging Face Daily Papers Papers

Summary

Adaptive Auto-Harness is a framework for sustained self-improvement of agentic systems deployed on open-ended task streams, outperforming baselines via a stateful multi-agent evolver, harness tree, and human-steering hooks.

Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on fixed offline benchmarks. Real deployments instead present open-ended task streams: histories grow without a fixed endpoint, heterogeneous tasks require different harnesses, and problem distributions shift over time. These challenges make a single repeatedly and densely updated harness brittle, causing performance degradation as accuracy peaks early and then declines. This motivates sustained harness construction with task-wise adaptation. We introduce Adaptive Auto-Harness, a framework and system for such streams. The framework decomposes the gap to an oracle harness into evolution loss and adaptation loss. The system addresses these losses with a stateful multi-agent evolver, a harness tree with solve-time routing, and human-steering hooks for cases where history lacks the needed signal. Across prediction-market, security-competition, and event-forecasting streams, Adaptive Auto-Harness outperforms five existing auto-harness baselines and ablations attribute gains to better construction, routing, or targeted human steering. Code is available in https://github.com/A-EVO-Lab/AdaptiveHarness .
Original Article
View Cached Full Text

Cached at: 06/03/26, 07:39 PM

Paper page - Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

Source: https://huggingface.co/papers/2606.01770

Abstract

Adaptive Auto-Harness framework addresses dynamic task streams by decomposing performance gaps into evolution and adaptation losses, utilizing a stateful multi-agent evolver and harness tree with solve-time routing for sustained performance improvement.

Auto-harness systemssuch as A-Evolve, GEPA, and Meta-Harness improveLLM agentsby optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on fixed offline benchmarks. Real deployments instead present open-ended task streams: histories grow without a fixed endpoint, heterogeneous tasks require different harnesses, and problem distributions shift over time. These challenges make a single repeatedly and densely updated harness brittle, causing performance degradation as accuracy peaks early and then declines. This motivates sustained harness construction with task-wise adaptation. We introduce Adaptive Auto-Harness, a framework and system for such streams. The framework decomposes the gap to an oracle harness intoevolution lossandadaptation loss. The system addresses these losses with astateful multi-agent evolver, aharness treewithsolve-time routing, andhuman-steering hooksfor cases where history lacks the needed signal. Across prediction-market, security-competition, and event-forecasting streams, Adaptive Auto-Harness outperforms five existing auto-harness baselines and ablations attribute gains to better construction, routing, or targeted human steering. Code is available in https://github.com/A-EVO-Lab/AdaptiveHarness .

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.01770

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.01770 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.01770 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.01770 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Continual Harness: Online Adaptation for Self-Improving Foundation Agents

Hugging Face Daily Papers

The paper introduces 'Continual Harness,' a framework enabling embodied AI agents to self-improve online without environment resets. It demonstrates significant progress in playing Pokémon games, achieving human-level performance through automated prompt and skill refinement.