MemTrace Boosts Long-Horizon Coding Agents
New memory system MemTrace significantly improves pass rates on long-horizon coding benchmarks by validating historical evidence.
ImportanceMaterialEvidenceE2 unreplicatedWrite-upQuick
The MemTrace system improved the pass@1 metric on the DeepSWE benchmark by 21.2 percentage points.
Long-horizon coding agents often face context overflow from extended execution trajectories or invalidation of earlier evidence due to repository changes. MemTrace uses immutable memory traces and a dependency graph to validate evidence against the current state before retrieval, fetching only what is needed for the next action.
Under the Codex CLI environment, the system also increased the SWE-EVO Resolved Rate by 4.4 points and the SWE-Milestone Score by 17.8 points. These are author-reported results, not yet independently reproduced.