hraness
Theme
Appearance

saved

An Empirical Study of Harness Design for Coding Agents

by Run-Ze Fan, Zihao Zhang, Simin Ma, Yebowen Hu, Shouju Wang, Kaiqiang Song, Fei Liu, Hamed Zamani and Xiaoyang WangarXivpublished

Hraness cites a source capture. The source author remains the source.

gist

Across 176 matched settings on SWE-Bench Verified and Terminal-Bench 2.1, this paper isolates planning, action space, and context management inside one fixed coding-agent loop. Context management pays off most when the window is tight, mainly by stopping overflow failures; staging rule-based elision before LLM summarization is the cheapest strong policy. Planning helps weaker models succeed and mainly saves cost for stronger ones, while bash-capable models can drop predefined tools and still win on CLI-heavy tasks at lower cost.

ideas

  • Component ablations beat harness bake-offs. Holding the execution loop fixed reveals when planning, tools, and context policy actually move accuracy versus cost.
  • Context management is a budget tool. Its value rises as the window shrinks, mostly by preventing overflow rather than rewriting agent behavior.
  • Elide, then summarize. Rule-based elision before selective LLM summarization beats recoverable-elision machinery that models barely use.
  • Planning changes role with model strength. Weaker models need it as an accuracy scaffold; stronger models mainly spend less with little accuracy change.
  • Action space should match bash skill. Predefined tools help weak bash users; bash-fluent models can run bash-only interfaces more cheaply on command-line tasks.

quotes

Context management becomes increasingly valuable as the context-window budget tightens

Run-Ze Fan et al., stating when context policy matters most.

Staging rule-based elision before LLM-based summarization provides the strongest overall efficiency

Run-Ze Fan et al., ranking context-management strategies.

Planning shifts from an accuracy scaffold for weaker models to a cost saver for stronger models

Run-Ze Fan et al., describing how planning's role changes with model strength.

bash-capable models can operate effectively with a bash-only interface and achieve substantially lower cost

Run-Ze Fan et al., advising when to drop predefined tools.