langchain-2026-deep-agents-harness · vendor-doc

Improving Deep Agents with harness engineering

Created: 2026 · Ingested: 2026-09-11

https://www.langchain.com/blog/improving-deep-agents-with-harness-engineering

Improving Deep Agents with harness engineering TLDR: Our coding agent went from Top 30 to Top 5 on . We only changed the harness. Here’s our approach to harness engineering (teaser: self-verification & tracing help a lot).

Referenced by

Claims in this catalog that draw on this source, and whether as support or counterpoint.

supportsA large share of an agent benchmark score is attributable to the harness around the model rather than the model itself: holding the model fixed and changing only guides, sensors, retries and state management is reported to move the same model from 30.9% to 74.6% on GAIA and 30th to 5th on Terminal Bench — so a score reported for "a model" on an agentic benchmark is a score for a model-plus-harness, and comparisons across labs with different harnesses are not comparisons of models.