Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-06-30 · high
The catch: stripping code first costs 12 points on SWE-bench Verified accuracy, per a new arXiv paper.
Why now: The paper posted to arXiv in June and its code is already public on GitHub, so teams running agents over large repos can test the tradeoff themselves right now.
Minifying code cuts a coding agent's input tokens 42% on average, according to a paper posted to arXiv in June. For agents that read whole repositories into context, that's real savings on cost and latency without touching the model itself. It comes at a price: accuracy on SWE-bench Verified drops 12 points when the code gets stripped down first.
The paper's case is that source code, not conversation history or tool output, is the dominant token sink for agents that keep full repo state in context. Minification strips non-essential lexical elements, things like whitespace and dead syntax, while preserving semantics, so the agent still sees working code, just less of it. The code behind the paper is public on GitHub.
I'd skip minifying the whole repo. The smarter move strips only the files an agent reads for context and leaves the ones it's actually editing untouched, since that's probably where the 12-point accuracy hit lands hardest. Worth watching whether anyone publishes numbers on selective minification instead of the blanket version.
The paper posted to arXiv in June and its code is already public, so teams running agents over large repos can test the tradeoff themselves this week.
Each link below shares sources, entities, or timing with this story.
Shared entities / Shared topic / Earlier coverage / Tension
Both cover GitHub, SWE, Verified; overlapping topics (code, coding, cost, token); earlier GitHub coverage from 2026-04-23.
Shared entities / Same source domain / Shared topic / What happened next
Both cover GitHub, SWE, Verified; reported by the same outlet (arxiv.org); overlapping topics (agent, cost).
Both cover GitHub, SWE, Verified; reported by the same outlet (arxiv.org); overlapping topics (agent, code).
Both cover GitHub, SWE, Verified; reported by the same outlet (arxiv.org); overlapping topics (agent, code).
Both cover SWE, Verified; reported by the same outlet (arxiv.org); overlapping topics (agent, average, code, coding).
Shared entities / Shared topic / Earlier coverage / Tension
Both cover SWE, Verified; overlapping topics (code, coding, cost, drop, token); earlier SWE coverage from 2026-02-17.
Shared entities / Shared topic / What happened next
Both cover GitHub, SWE, Verified; overlapping topics (agent, code, token); picks up the GitHub thread on 2026-08-15.
Shared entities / Same source domain / Shared topic / What happened next / Downstream implication
Both cover SWE, Verified; reported by the same outlet (arxiv.org); overlapping topics (agent, code).