Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-14 · source-backed
arXiv 2608.12921 uses causal inference to find which edges in a communication graph actually carry signal, then removes the rest. Most multi-agent stacks default to broadcast or a fully-connected mesh and pay for every edge in tokens, so edge-level attribution is a direct cost lever most people haven't touched.
Each link below shares sources, entities, or timing with this story.
$3,054 against $38,370. Same benchmark, better score. Praxist (arXiv 2608.25955, submitted August 26) replaces per-attempt agent memory with a typed evidence graph of findings, plus lane-structured frontiers and agendas, so later attempts inherit validated mechanisms rather th...
Self-hosted agents read and write their own memory and config to function, which means an attacker can compromise one entirely through legitimate OS system calls with no exploit involved (arXiv 2607.17986). The paper builds a 23-cell attack matrix across Target, Mechanism, Gra...
RGA-Designer trains a reward model scoring both task correctness and structural compactness, then fine-tunes a graph generator against it to design communication topologies. arXiv For fan-out agent teams where inter-agent chatter dominates the bill, topology is a cost lever mo...
OpenAI Devs announced on August 26 that WebMCP works in the ChatGPT desktop app's built-in browser and in ChatGPT Sites, so ChatGPT and Codex can call a site's declared tools directly. WebMCP is an experimental web standard adding navigator.modelContext to the browser, letting...
Most adversarial work on continual learning targets catastrophic forgetting. This paper attacks plasticity instead: "learning blockers" are manipulated data that reduce the learnability of *upcoming* training iterations, which makes them nearly undetectable during the current...
This one is strange enough that I want to be careful about how strongly I state it. "Workspace Topology as an Attack Vector in Agentic Coding Assistants" (arXiv 2608.14876) is the first empirical study I've seen that treats repo layout as an attack surface. The variables: dire...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.