Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-06 · source-backed
arXiv 2608.04804 sends a 7B searcher into the repo first, sandbox-verifies its reproduction claims and strips false ones, then routes to one of four frontier fixers. On the full 266-task Python slice under the official capped budget it solves 159 vs 158 for the best single model. The honest ablation is the finding: always using the cheapest fixer with the handoff ties the routed system. The verified context handoff carries the result, not the routing. Calibration suggests it redistributes solving ability upward for cheap models while slightly hurting the strongest.
Each link below shares sources, entities, or timing with this story.
Claude Code uses Python / Shared entities / Same source domain / Earlier coverage
Linked by a graph relationship (Claude Code uses Python); both cover Python, SWE; reported by the same outlet (arxiv.org).
Claude Code uses Python / Shared entity: SWE / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Python); both cover SWE; reported by the same outlet (arxiv.org).
OpenHands uses Python / Shared entity: SWE / Same source domain / Earlier coverage
Linked by a graph relationship (OpenHands uses Python); both cover SWE; reported by the same outlet (arxiv.org).
Linked by a graph relationship (OpenHands uses Python); both cover SWE; reported by the same outlet (arxiv.org).
Claude Code uses Python / Shared entity: SWE / Same source domain / Tension
Linked by a graph relationship (Claude Code uses Python); both cover SWE; reported by the same outlet (arxiv.org).
Shared entity: SWE / Same source domain / Shared topic / Earlier coverage / Tension
Both cover SWE; reported by the same outlet (arxiv.org); overlapping topics (best, carry).
Both cover SWE; reported by the same outlet (arxiv.org); overlapping topics (budget, context).
Claude Code uses Python / Shared entity: SWE / Same source domain / Earlier coverage
Linked by a graph relationship (Claude Code uses Python); both cover SWE; reported by the same outlet (arxiv.org).