A deterministic runtime layer that tracks a coding agent's reads, edits, and repeated commands raises Pass@1 on SWE-bench Verified by up to 8 points and cuts cost by up to 32 percent, with no extra model calls.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents
A deterministic runtime layer that tracks a coding agent's reads, edits, and repeated commands raises Pass@1 on SWE-bench Verified by up to 8 points and cuts cost by up to 32 percent, with no extra model calls.