Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
🤗 Upvotes: 172 | cs.AI, cs.SE
Authors:
Ruhan Wang, Yucheng Shi, Zongxia Li, Zhongzhi Li, Yue Yu, Junyao Yang, Kishan Panaganti, Haitao Mi, Dongruo Zhou, Leoweiliang
Title:
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Arxiv:
http://arxiv.org/abs/2607.13285v1
Abstract:
The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing ease inspection, but still leave this behavior-to-code mapping to be recovered by hand. Behavior localization is therefore a central bottleneck in harness evolution. We introduce the Harness Handbook, a behavior-centric representation synthesized automatically from a harness codebase via static analysis and LLM-assisted structuring, linking each behavior to its corresponding source. We also introduce Behavior-Guided Progressive Disclosure (BGPD), which guides agents from high-level behaviors to relevant implementation details and verifies candidate locations against the current source. On diverse modification requests from two open-source harnesses, Handbook-Assisted planning improves behavior localization and edit-plan quality while using fewer planner tokens, with the largest gains on scattered sites, rarely executed paths, and cross-module interactions. Evolving complex agentic systems thus depends not only on generating edits, but also on determining where those edits should be made.
You May Also Like

Vida Eterna. Respuestas desde la Ciencia | Dr. Manuel Sans Segarra
Dr. Manuel Sans Segarra

Trent Loos Podcast
Trent Loos

The 365 Days of Astronomy
365DaysOfAstronomy.org

Real Ghost Stories Online
Real Ghost Stories Online | Paranormal, Supernatural & Horror Radio

Breaking Down: Collapse
Kory & Kellan

The Grave Talks | Haunted, Paranormal & Supernatural
Ghost Stores, Haunted, Paranormal & Supernatural Stories

The Biotech Startups Podcast
Excedr

The Best of Coast to Coast AM
iHeartPodcasts and Coast to Coast AM

Eye On The Sky
Vermont Public

Мослекторий
Москва 24
Community discussion