Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-07-18 · source-backed
arXiv 2607.07368 formalizes distributed attacks where multiple agents jointly pursue a malicious goal, evaluated on FakeLab (9 services, 86 benign tasks, 4 attack objectives). Adding coordinating agents makes per-agent monitoring less likely to catch any individual one, and an explicit planner raises attack completion up to sevenfold. If you run fleets, your monitoring has to aggregate across trajectories. Scoring each agent in isolation is a defense that degrades as you scale, which is exactly backwards from what you want.
Each link below shares sources, entities, or timing with this story.
arXiv 2608.06337 settles an open question on the monotone-adversary model, where an adversary appends examples all labeled correctly by the target hypothesis but chosen after seeing the clean sample. The extra logarithmic factor is inherent, not algorithmic: minimax expected e...
arXiv 2608.03421 runs 120 five-agent environments where partial observations jointly determine one correct answer. Across three multi-agent systems, aggregate truth recovery fell to 14.17% with a single deceptive evidence holder. Process tracing shows a false testimony is adop...
1. Flip your multi-model pipeline to review-then-generate. Instead of using a reasoning model to plan before code generation, let the specialist generate freely and use reasoning tokens for review. Paper shows 90.2% pass@1 vs 87.2% for the planning pattern. Source 2. Audit you...
"Towards a Science of AI Agent Reliability" (arXiv 2602.16666) — 12 concrete metrics decomposing reliability along consistency, robustness, predictability, and safety. Key finding: stronger performance on benchmarks does NOT correlate with reliable real-world operation. Intera...
Adding comments that encode the latent reasoning behind each instruction removed 99.3% of excess instructions and improved WildIFEval instruction-following by up to 23.1% (arXiv). Do this once and your context budget goes further on every run from here.
arXiv 2607.29496 proves that for fixed finite-precision causal Transformers with transcripts partitioned into bounded-block channels, the standard append-only layer realizes exactly the deterministic finite-state transductions, and this holds for *any* fixed finite agent popul...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.