Metraipolis › archive › dc_75e2f36ed4bb
MemTrace: State-Consistent Memory for Long-Horizon Coding Agents — arXiv:2610.04838
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04838
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:24:50.344Z
- SHA-256 of the archived text
567c50cbe2c023137a3b35b21f19b8ffe9887800a4a47c1318fe349a26c9676c- Stable URL of this page
https://metraipolis.com/documento/dc_75e2f36ed4bb
How to cite
MemTrace: State-Consistent Memory for Long-Horizon Coding Agents — arXiv:2610.04838 — arXiv, https://arxiv.org/abs/2610.04838 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75e2f36ed4bb (Metraipolis archive dc_75e2f36ed4bb, sha256 567c50cbe2c023137a3b35b21f19b8ffe9887800a4a47c1318fe349a26c9676c)
BibTeX
@misc{dc75e2f36ed4bb,
title = {MemTrace: State-Consistent Memory for Long-Horizon Coding Agents — arXiv:2610.04838},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04838},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75e2f36ed4bb; sha256 567c50cbe2c023137a3b35b21f19b8ffe9887800a4a47c1318fe349a26c9676c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04838. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated histories strain context budgets, and (2) repository changes can invalidate earlier execution evidence. Existing approaches address these challenges through techniques like larger context windows, compression, retrieval, or repository representations, but often fail to reconstruct a consistent task state after a context refresh or verify whether recalled evidence remains valid. Thus, we introduce MemTrace, a provenance-aware memory system that preserves execution history and aligns its reuse with the evolving task (e.g., iterative cross-file repair) and repository state. MemTrace stores history as immutable Memory Traces anchored to key information (e.g., files, symbols, tests), and organizes their execution order and dependencies in a Memory Trace Graph. When context is constrained, working memory retains only compact Memory Anchors, from which the agent can reconstruct the latest execution state and locate evidence relevant to its next action. Before restoring historical evidence, MemTrace checks its validity against the current repository state and retrieves only what the next action requires. Across three complementary long-horizon coding benchmarks, MemTrace consistently outperforms all fully evaluated baselines under the same backbone and harness, improving DeepSWE pass@1 by 21.2 points, SWE-EVO Resolved Rate by 4.4 points, and SWE-Milestone Score by 17.8 points under Codex CLI. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.04838 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:05.524Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).