\begin{enumerate}\setlength{\itemsep}{1pt}\renewcommand{\labelenumi}{(\roman{enumi})}
\item On competitive programming with Claude Haiku~5.5, most of what the loops found is standard engineering. The
model's reasoning often exhausts the starting agent's 4{,}096-token output cap on hard problems, and the agent then stops on an
empty turn, a response with neither text nor a tool call. One textbook move, L, which rewrites the agent's model calls
with a 16{,}000-token output cap, comes within about a tenth of the best loop agent's gain at less than half its cost
per task; in each of two sets of five one-shot redesigns by Claude Opus~5.5, one made with failure logs and one without,
four also raise the cap, to 8{,}192 tokens. Even the best combinations of textbook moves remain one to five points below the best loop agent
(\S\ref{sec:results2}; Table~\ref{tab:hyp} gives the registered verdicts).
\item Generic requests come close to the DGM's diagnoses only when some of them target the empty-turn failure: without
such requests, random-diagnosis loops gain $\rcHfourteenAbs$ points less than the DGM loops (\S\ref{sec:random-clean}).
\item On SWE-bench Verified tasks outside the DGM's evaluation set, run in the DGM's harness with Claude Sonnet~4.5 (a newer model than the
DGM used), the released best agent does not improve significantly on its initial agent, and about half of the best agent's runs end
before a patch is recorded, for a cause we could not determine. The initial agent with three textbook moves does better than the best agent at a quarter of
the best agent's cost, also when the patches of those runs are kept and when both DGM agents are given the same
16{,}000-token cap (\S\ref{sec:published}).
\item Placebo loops raise their best score on the selection tasks by as much as order statistics predict. For the six DGM
loops of the first two rounds, the gain on the selection tasks exceeds the gain on fresh problems by about four points
on average, which is not significant (\S\ref{sec:round1} and Figure~\ref{fig:main}).
\end{enumerate}
Section~\ref{sec:published} also re-runs the agents discovered by ADAS, which, under a current model, do no better than chain-of-thought
self-consistency with a matched number of samples on three of four benchmarks, and reports a leak of hidden-test
information in the DGM's SWE-bench harness: in the three tasks we inspected, a leftover pytest cache named the failing
hidden tests. Our runs remove the leak, and none of the DGM's released chats reads the cache. Appendix~\ref{app:othermodels}
shows that the textbook moves together help under Claude Haiku~4.5 but do not transfer to gpt-oss-120b (exploratory).