Metraipolis › archive › dc_a3aa223a80ee
ReConMem: A Graph-Based Dual Memory System for Repository-Oriented Conversations — arXiv:2611.07759
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07759
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:51:30.672Z
- SHA-256 of the archived text
0d4e81001b2721cca67f04133e03188d7c5596f4bcf82453f10b707ae105518e- Stable URL of this page
https://metraipolis.com/documento/dc_a3aa223a80ee
How to cite
ReConMem: A Graph-Based Dual Memory System for Repository-Oriented Conversations — arXiv:2611.07759 — arXiv (en), https://arxiv.org/abs/2611.07759 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3aa223a80ee (Metraipolis archive dc_a3aa223a80ee, sha256 0d4e81001b2721cca67f04133e03188d7c5596f4bcf82453f10b707ae105518e)
BibTeX
@misc{dca3aa223a80ee,
title = {ReConMem: A Graph-Based Dual Memory System for Repository-Oriented Conversations — arXiv:2611.07759},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07759},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3aa223a80ee; sha256 0d4e81001b2721cca67f04133e03188d7c5596f4bcf82453f10b707ae105518e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07759. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-based code assistants are increasingly used in iterative repository-level development, where effective assistance requires jointly leveraging evolving conversational history and repository context. Existing memory systems, however, are primarily designed for general-purpose conversations and do not sufficiently coordinate conversational information with the structured code entities to which it refers. We propose ReConMem, a graph-based dual memory system for repository-oriented conversations. ReConMem organizes distilled conversational memories and conversation-relevant code entities into interconnected semantic and structural memory graphs, while maintaining their cross-graph associations as interactions evolve. For memory recall, ReConMem combines natural-language and code-aligned retrieval through code-draft-based query grounding, expands retrieved information over intra- and inter-graph relations, and compresses retrieved code according to its structural granularity. We evaluate ReConMem on two repository-oriented conversational benchmarks spanning long-horizon context management and realistic project-grounded multi-turn assistance. On LoCoEval, ReConMem improves Pass@1 over the strongest baseline by 7.917 and 7.292 percentage points on single-hop and multi-hop subsets, respectively, with comparable context compression. On CodeAssistBench, it achieves 27.61% Correct and 44.03% Partially Correct, exceeding Full History by 4.10 and 7.09 percentage points, respectively, while improving interaction quality. These results demonstrate that aligning conversational memory with repository structure improves context management for repository-oriented multi-turn interactions. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2611.07759 — 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 2026-11-06T14:21:57.532Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).