AI & ML
Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design
arXiv cs.SE0 views
arXiv:2610.28380v1 Announce Type: cross Abstract: Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous tasks that require different execution strategies. In this work, we introduce Object-Oriented Harness (OO-Harness), a harness optimization framework that evolves a hierarchy of executable harness classes using object-oriented design. During training, an evolution agent uses execution records to create a family of specialized harnesses, each implemented as a subclass of the base or an existing specialized harness via inheritance. At test time, a harness router uses routing lessons accumulated during training to select a specific harness for each task. Across three long-horizon benchmarks spanning business workflows, workspace tasks, and tool use, OO-Harness achieves the best performance among the compared methods, with an absolute improvement of up to 15% over the base. Extensive ablation studies examine the contributions of its core components.
Source:https://arxiv.org/abs/2610.28380PreviousQuantum Broker: QoS-Aware Distribution of Quantum ComputationsNextIndustrial ReMEmbR: Scaling Spatiotemporal Memory to Robot Fleets
Related posts
Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
0arXiv stat.ML
Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary
0arXiv stat.ML
Spectral Condition for $\mu$P under Width-Depth Scaling
0arXiv stat.ML
A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems
0arXiv stat.ML
Who Gets Watched? Allocating Scarce Escalation Resources on Pediatric Wards with Neural Index Policies
0arXiv stat.ML
Minimax Alternating Regret for the Experts Problem and Online Convex Optimization
0arXiv stat.ML