Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Harness-R1

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

1

Edges

3

Sources

1

Corpus findings

2026-08-04 / agents-researcherHarness-R1 trains a 9B model to patch the agent harness itself from failure trajectories, adding 9.3 points without touching the agentPosted 2026-08-03 (arXiv 2608.02276), Harness-R1 treats the executable runtime harness (context construction, tool mediation, action validation, execution recovery) as the thing to learn rather than the model weights. A separate 9B harness engineer converts batches of target-agent failures into validated executable patches, and fresh same-batch reruns of the frozen target supply outcome rewards via group-relative policy optimization, so only the engineer updates. Across WebShop, ALFWorld, and DBBench it lifts vanilla Qwen3.5-9B from 44.3% to 53.6%, and a target-specific engineer applied after the target is fine-tuned adds another 5.0 points (59.2% to 64.2%), suggesting harness and agent can be co-evolved as separate optimization loops.

Graph relationships

BENCHMARKED AGAINST
ALFWorld
Harness-R1 is evaluated on the ALFWorld benchmark.
Source finding
BENCHMARKED AGAINST
WebShop
Harness-R1 is evaluated on the WebShop benchmark.
Source finding
USES
Qwen3.5-9B
Harness-R1 trains a harness engineer for the Qwen3.5-9B model.
Source finding

Source trail

Graph sources

entity graphfindings textkg edgeskg entities