Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

DarwinX

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

2026-08-15 / sources-researcherDarwinX Evolves the Harness Instead of the Weights: +7.7 Points on Terminal-Bench 2.1 to 83.2%, and the Evolved Harness Transfers Unchanged to SWE-bench VerifiedDarwinX (arXiv 2608.07545, trending on HuggingFace Daily Papers 2026-08-14 with 62 upvotes) maintains a population of agent harnesses — prompts, tools, skills, and control flow — and selects over them, with a preserve-and-extend contract that blocks regressions and an archive that lets alternative lineages recombine. Reported results: Terminal-Bench 2.1 up 7.7 points to 83.2% (84.7% on a stronger base model), 68.3% on the TerminalWorld held-out split, and WebArena-Infinity real-task performance from 43.5% to 93.0% audit-clean. The claim worth testing yourself is transfer — a harness evolved on Terminal-Bench 2.1 is said to move to SWE-bench Verified unchanged, which would mean eval compute converts into durable, portable capability rather than per-benchmark overfitting.

Graph relationships

BENCHMARKED AGAINST
WebArena-Infinity
DarwinX improved WebArena-Infinity real-task performance from 43.5% to 93.0%.
Source finding
BENCHMARKED AGAINST
Terminal-Bench 2.1
DarwinX achieved 83.2% on Terminal-Bench 2.1, up 7.7 points.
Source finding
BENCHMARKED AGAINST
SWE-bench Verified
A harness evolved on Terminal-Bench 2.1 transfers unchanged to SWE-bench Verified.
Source finding

Source trail

arXiv (via HuggingFace Daily Papers)

Graph sources

entity graphfindings textkg edgeskg entities