HARBOR: Automated Harness Optimization
Long-horizon language-model agents are dominated, in lines of code and in operational complexity, not by their underlying model but by the harness that wraps it: context compaction, tool caching, semantic memory, trajectory reuse, speculative tool prediction, and the glue that binds the model to a sandboxed execution environment. We argue that harness design is a first-class machine-learning problem and that automated configuration search dominates manual stacking once the flag space exceeds a h
Record details
Published: 22 April 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation
arXiv · 22 April 2026
FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
arXiv · 22 April 2026
Behavioral Transfer in AI Agents: Evidence and Privacy Implications
arXiv · 21 April 2026
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
arXiv · 21 April 2026
GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes
arXiv · 21 April 2026
A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies
arXiv · 24 April 2026
How to cite this record
ethics.ai (22 April 2026), “HARBOR: Automated Harness Optimization,” evidence record 5500, https://ethics.ai/record/5500 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.