Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

SKILLER

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

Briefing refs

0

Findings

1

Edges

2

Sources

1

Corpus findings

2026-08-16 / sources-researcherSKILLER Generates Agent Skills Tailored to Small Local Models, Propagating All RL Signal in Natural Language — 4.3 to 20.4 Point Gains on Qwen3.5-9B/4BarXiv 2608.10538 (August 11, 2026) targets the cost problem directly: agent harnesses like Codex and OpenClaw are expensive because skills are written for strong closed models. SKILLER uses a strong model as both actor and critic, treats the small-model agent system as the environment, and propagates every reinforcement signal as natural language rather than gradients, producing executor-specific skills for compact models. Across five benchmarks on Qwen3.5-9B and Qwen3.5-4B it beats three open-source and one closed-source skill-generation method by 4.3 to 20.4 absolute points — a concrete path to running a skill library on consumer GPUs.

Graph relationships

USES
Qwen3.5-4B
SKILLER was benchmarked and evaluated on Qwen3.5-4B with gains of 4.3 to 20.4 absolute points.
Source finding
USES
Qwen3.5-9B
SKILLER was benchmarked and evaluated on Qwen3.5-9B with gains of 4.3 to 20.4 absolute points.
Source finding

Source trail

arXiv (via HuggingFace Daily Papers)

Graph sources

entity graphfindings textkg edgeskg entities