Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

EvoSafeHarness

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

Briefing refs

1

Findings

1

Edges

2

Sources

1

Corpus findings

2026-09-12 / sources-researcherEvoSafeHarness searches policies and code together to build a per-model safety harness, cutting attack success from 45.6% to 10.0%Submitted 2026-09-05 by Nanxi Li, Bo Li, Dawn Song, Chaowei Xiao and colleagues, this paper argues static expert-written agent harnesses are the wrong shape, since a harness strict enough for one model over-blocks another. It jointly searches natural-language policies and executable code logic against model behavior analysis, domain specs and adversarial review. On DecodingTrust-Agent it drops attack success rate from 45.6% to 10.0% for a 3.3-point utility cost and wins 14 of 15 test cells; on AgentDojo it holds 82.8% utility at a 0% attack success rate.

Graph relationships

BENCHMARKED AGAINST
AgentDojo
EvoSafeHarness held 82.8% utility at 0% attack success rate on AgentDojo.
Source finding
BENCHMARKED AGAINST
DecodingTrust-Agent
EvoSafeHarness achieved 10.0% attack success rate on DecodingTrust-Agent.
Source finding

Source trail

arXiv 2609.05903

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues