Search papers, labs, and topics across Lattice.
This paper introduces the Harness Handbook, a behavior-centric representation that utilizes static analysis and LLM-assisted structuring to automatically synthesize a mapping between high-level behaviors and their corresponding code locations in AI agent harnesses. The authors highlight the challenges of behavior localization in evolving harnesses, which are often large and tightly coupled, making it difficult for developers to identify necessary code modifications. Their approach, incorporating Behavior-Guided Progressive Disclosure (BGPD), significantly enhances the quality of edit-planning and behavior localization, particularly for complex and distributed codebases.
Behavior localization is revolutionized, enabling developers to seamlessly connect high-level modification requests to specific code locations in complex AI harnesses.
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.
