Policy dependency / Stack layer
Retrieval that crosses into your dependencies' source, not just your repo, adds up to 6.3% pass@1 and survives version changes
arXiv 2609.09987
Stack layer / Threat pattern
A spec-first agent framework taxonomy: persuasion, front-loaded structure, or controls the agent cannot edit
arXiv 2609.09671
Stack layer / Threat pattern
NCP-ArchPreview reaches OLMo-3-7B's final pretraining loss on 51.3% of the tokens by predicting multi-token concepts
arXiv / HuggingFace Daily Papers
Stack layer / Threat pattern
100 LLM agents running a simulated town economy for 26 weeks froze the money supply: 0.3% of prices ever changed, and memory deletion made no difference
arXiv
Stack layer / Threat pattern
AgentAudit attaches to a running agent and scores its trace on ten dimensions, exposing 95.1 vs 22.6 trust spreads at similar task completion
arXiv
Stack layer / Threat pattern
Show-Harness gets frontier VLMs controlling robots zero-shot through discrete semantic action units
arXiv
Policy dependency / Stack layer
CROSS-CATEGORY: Three Independent Agent-Action Gates Shipped in 48 Hours, All Judging the Command Against Stated Intent
Product Hunt, github.com/AGGIB/Stroq and rewarelabs.com (three independent sources; the 72% figure is Reware's own)
Stack layer / Threat pattern
Audio prompt injection completes in 49% of cells where images complete in 1%, across 720 runs on six agent frameworks
arXiv