Fetching from the wire…
01
02
03
04
05
06
07
08
Skills2026-08-11 · source-backed
RETRACE has a verifier infer what problem the patch appears to solve using only the patch and trajectory, then compares that inference against the real issue. Training-free, lifted Pass@1 by 7.0% and 3.6% on mini-SWE-agent over SWE-bench Verified. The information-hiding trick generalizes to any LLM-judge setup where the judge would otherwise inherit the generator's misreading.
Each link below shares sources, entities, or timing with this story.
Simon Willison released LLM / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover SWE, Verified; earlier SWE coverage from 2026-04-23.
Simon Willison released LLM / Same source domain / Shared topic / Tension
Linked by a graph relationship (Simon Willison released LLM); reported by the same outlet (arxiv.org); overlapping topics (against, agent).
Simon Willison released LLM / Shared entity: Verify / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover Verify; overlapping topics (against, agent).
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-07-27.
Simon Willison released LLM / Shared entity: SWE / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover SWE; earlier SWE coverage from 2026-04-25.
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-18.
Simon Willison released LLM / Shared entity: SWE / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover SWE; earlier SWE coverage from 2026-03-17.