Fetching from the wire…
Research2026-09-01 · source-backed
AgentLogs scanned 1,812,362 public repositories and captured agent activity from 35,810, yielding 307,416 tasks, 549,239 sessions and 64,255,174 log entries including prompts, intermediate reasoning, tool calls and token usage (arXiv 2608.29204). Prior datasets captured what agent pull requests looked like when finished. This captures the process, which is the raw material for studying failure modes and per-task cost empirically.
Each link below shares sources, entities, or timing with this story.
First standardized benchmark for AI agent skills. 86 tasks, 11 domains, 7,308 test trajectories. Critical finding: curated skills +16.2%, self-generated skills +0%. Run it against your own skills. GitHub | Paper
arXiv 2607.29677, from a team including Adrian Lyjak and Simon Suo, evaluates schema-guided extraction across 370 enterprise documents, 4,869 pages, 8 domains and 67 document types, scoring order-insensitive value F1, word-level grounding F1 and page-level grounding F1 separat...
Microsoft confirmed on June 16 it's routing GitHub traffic through AWS after autonomous coding-agent activity pushed past reliability thresholds: 275M commits a week, nine outages in May, June availability dropping below the 99.9% enterprise SLA. This is the capability-versus-...
Every AI-productivity fight this year has been three people quoting three studies at each other. Field experiments say +26% more tasks per week. METR's randomized trial says a 19% slowdown. Team telemetry says code review time up 441%. Pick your number, pick your priors, argue...
This one annoyed me, in the good way. Researchers took 206 real developer-agent sessions from 13 developers, extracted each developer's preferences from their actual interaction traces via rule-based bootstrapping plus evidence-grounded refinement, then replayed everything aga...
This is the most directly usable paper of the day and it does something rare: it bolts onto an existing agent without touching it. Ledger is a deterministic runtime wrapper that distills an agent's completed interactions into explicit state. What has been observed, what has be...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.