Story · arXiv
ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents (arXiv)
paper · Story page
ContextPipe treats prompt assembly, what goes in, in what order, when to compact, as database query execution: a five-phase pipeline with a source catalog, a deterministic cache-aware optimizer, and an EXPLAIN ANALYZE style trace. A preliminary run on the SWE-bench Pro Qutebrowser subset cut tokens by 31% and LLM calls by 23% against append-only assembly, at the cost of a lower KV cache-hit ratio.
In plain words
- Researchers created ContextPipe, which decides what information long-running artificial intelligence tools receive for each task.
- It separates preparation into five fixed stages that choose sources, arrange information, improve the plan, run it, and learn from results.
- Its source list and predictable decision rules let people repeat and inspect exactly how each input was prepared.
- In an early test, it processed 31% less text and made 23% fewer calls to the language system.
- For builders, the design makes input preparation easier to audit and individual failures easier to isolate.
Appeared in
- Google's Mantis bug-fixing harness, and privilege escalation in 12 agent harnesses
Sep 03, 2026 · in the sections
Subscribe
Get the brief in your inbox
Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.
- Weekdays at 8:45am IST, one lead story and 6 to 9 items.
- Sundays, an argued synthesis rather than a recap.
- One click to leave, and quiet days say so in the subject line.