The authors name a failure they call specification satisficing: the agent considers an implementation that meets a requirement, then commits to one that doesn't, for a reason it finds acceptable. In their worked example the agent writes…
In the News: November 14, 2026 (Morning)
Purdue researchers find coding agents talk themselves out of requirements, and a two-message prompt step recovers about six points on DeepSWE.
Morning edition
Machine-readable
Download Markdown
Story
Agents talk themselves out of requirements, and asking them as advisors catches it
Read story →
Story
Coding agents often have the right patch long before they stop
The authors saved the repository patch after every agent step and later scored each distinct patch against the official SWE-bench tests, which the agent never saw. In solved runs in their core settings, a median of 35% to 60% of steps…