Metraipolis › archive › dc_1c2fe0ebcf01
Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory — arXiv:2608.10676
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10676
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:33.905Z
- SHA-256 of the archived text
85627c8ac111b3d78b6ded7f3c58e6a980e03bda77aa12e081f418ecd275e604- Stable URL of this page
https://metraipolis.com/documento/dc_1c2fe0ebcf01
How to cite
Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory — arXiv:2608.10676 — arXiv (en), https://arxiv.org/abs/2608.10676 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1c2fe0ebcf01 (Metraipolis archive dc_1c2fe0ebcf01, sha256 85627c8ac111b3d78b6ded7f3c58e6a980e03bda77aa12e081f418ecd275e604)
BibTeX
@misc{dc1c2fe0ebcf01,
title = {Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory — arXiv:2608.10676},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10676},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1c2fe0ebcf01; sha256 85627c8ac111b3d78b6ded7f3c58e6a980e03bda77aa12e081f418ecd275e604},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10676. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments. However, providing complete execution trajectories to the LLM causes unbounded context growth and introduces noise. Existing compression methods reduce context at the cost of important details and often replace erroneous facts without repairing downstream reasoning derived from them. To address this problem, we propose ReTree, a self-correcting tree-structured memory mechanism for search agents. ReTree constructs a bounded per-step reasoning context while preserving source-linked evidence. It models search as an evidence tree whose nodes store bounded summaries, evidence, and revision histories. When newly retrieved evidence contradicts an earlier claim, ReTree traces back to the node where the claim was introduced, replaces outdated evidence, regenerates summaries, prunes affected branches, and resumes search. Source-grounded evidence provenance supports reliable conflict localization and keeps final claims traceable to retrieved passages. Experiments on four public question-answering and search benchmarks show that ReTree consistently outperforms Full-Trajectory ReAct, improving answer accuracy by up to 25.6 percentage points (pp); the average maximum per-step reasoning context of Full-Trajectory ReAct is $1.27$--$1.51\times$ that of ReTree. These results establish ReTree as an effective self-correcting memory abstraction for long-horizon search. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.10676 — 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 2026-10-19T05:57:28.291Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).