Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

Key points

• Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks.1
• However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long interaction histories, context explosion, and semantic drift.1
• To address these challenges, we introduce Dev-Primitives (Development Primitives), a modular and executable abstraction that transforms repository components from passive software artifacts into active participants in software engineering.1
• Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an agent-native interface grounded in its own implementation and dependencies, enabling natural-language reasoning, inter-component communication, and localized self-modification.1

Sources (1)

• [1]Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 06:32 AM

  Building on Dev-Primitives, we propose HERMES, a Harness Engineering framework for software engineeRing via Modular Executable Dev-PrimitiveS, which instantiates these primitives at repository scale through a dependency-aware dynamic activation mechanism and a bug diagnosis mechanism that maps execution evidence back to the components that must be revised.

  Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks.

Extractive summary: sentences quoted from the sources.