Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-04 · high
A separate harness engineer model rewrote a frozen 9B agent's runtime, raising task success from 44.3% to 53.6%.
Why now: The paper posted to arXiv in August 2026, with its 9.3-point gain tested so far only on WebShop, ALFWorld, and DBBench.
Harness-R1 lifts a frozen 9B Qwen agent's task success from 44.3% to 53.6% by training the runtime around it instead of the model, per a paper posted to arXiv.
That's a 9.3-point jump in task success without retraining the agent model at all. The gain shows up on WebShop, ALFWorld, and DBBench, benchmarks that test whether an agent actually finishes real tasks.
A separate harness engineer model watches the frozen target agent fail. It converts those failures into validated, executable patches to the harness. That's the code that builds context, mediates tool calls, validates actions, and recovers when execution breaks.
The harness engineer gets rewarded by rerunning the same batch of tasks against the frozen target agent after each patch lands. No new weights for the agent itself, just a better runtime wrapped around the same model.
Vanilla Qwen3.5-9B starts at 44.3% task success. Add the trained harness engineer and it climbs to 53.6%, a 9.3-point gain. Stack a second, target-specific harness engineer on top of the one already fine-tuned, and it adds another 5.0 points.
A one-time patch would be enough if the harness fix generalized cleanly. It doesn't. The extra 5 points from a target-specific engineer means the runtime around an agent needs the same per-deployment tuning prompts and fine-tunes already get. The paper doesn't say what a second training pass costs per deployed agent, or how the approach holds up past these three benchmarks.
Each link below shares sources, entities, or timing with this story.
SkillPyramid benchmarked against ALFWorld / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (SkillPyramid benchmarked against ALFWorld); both cover ALFWorld, WebShop; reported by the same outlet (arxiv.org).
Shared entities / Same source domain / Shared topic / Earlier coverage
Both cover ALFWorld, WebShop; reported by the same outlet (arxiv.org); overlapping topics (adding, agent, alfworld, context, convert).
Shared entity: Harness / Same source domain / Shared topic / Earlier coverage / Tension
Both cover Harness; reported by the same outlet (arxiv.org); overlapping topics (action, agent, context, harness).
Shared entities / Same source domain / Shared topic / Earlier coverage
Both cover ALFWorld, WebShop; reported by the same outlet (arxiv.org); overlapping topics (agent, alfworld).
Shared entity: ALFWorld / Same source domain / Shared topic / Earlier coverage
Both cover ALFWorld; reported by the same outlet (arxiv.org); overlapping topics (agent, alfworld, context).
Shared entity: Harness / Shared topic / Earlier coverage / Tension
Both cover Harness; overlapping topics (agent, context, harness); earlier Harness coverage from 2026-04-01.
Shared entity: Harness / Same source domain / Shared topic / Earlier coverage
Both cover Harness; reported by the same outlet (arxiv.org); overlapping topics (agent, harness).
Both cover Harness; reported by the same outlet (arxiv.org); overlapping topics (agent, context).