Coding-agent harness choices should match model skill and context budget

Across 176 matched configurations, the authors isolate how planning, tool interfaces, and context management affect coding-agent accuracy, cost, and trajectory length.

Industry
Run-Ze Fan · Zihao Zhang · Simin Ma · Yebowen Hu · Shouju Wang · Kaiqiang Song · +3 more

UMass Amherst · Zoom Video Communications · Emory University · UNC Charlotte

Research Digest··2 min read
Fan et al.

The authors fixed the harness’s core execution loop and varied planning, available actions, and context-management strategy.

Why this paper

From UMass Amherst and 3 others · Part of Agent Harness Optimization, now 61 papers

In one line

Coding harness components are conditional: context management matters as context shrinks, planning helps weak models at accuracy and strong models at cost, and bash-only suits capable models.

What we could check

  • ·No code link found
  • ·No weights link found
  • ·No dataset link found
  • ·No compute details found
  • ·No stated limitations found
  • ·No benchmark numbers found

Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.

§
newspaper

Research Digest

Articles published under the Zotpaper byline are synthesized from multiple source publications by our AI editor and reviewed by our editorial process. Each story combines reporting from credible outlets to give readers a balanced, comprehensive view.