Metraipolis › archive › dc_a802ffa5650b

ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval — arXiv:2608.12720

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12720
License (as archived)
CC0-1.0
Archived
2026-10-19T04:18:05.898Z
SHA-256 of the archived text
9694aaa9daccda3a698755fcd0c47dce640f50be0d02fb210230bfdc0c8fbbd9
Stable URL of this page
https://metraipolis.com/documento/dc_a802ffa5650b

How to cite

ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval — arXiv:2608.12720 — arXiv (en), https://arxiv.org/abs/2608.12720 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a802ffa5650b (Metraipolis archive dc_a802ffa5650b, sha256 9694aaa9daccda3a698755fcd0c47dce640f50be0d02fb210230bfdc0c8fbbd9)
BibTeX
@misc{dca802ffa5650b,
  title = {ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval — arXiv:2608.12720},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12720},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a802ffa5650b; sha256 9694aaa9daccda3a698755fcd0c47dce640f50be0d02fb210230bfdc0c8fbbd9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12720. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely treated as evolvable components. This static approach limits performance on heterogeneous memory queries, which often demand diverse evidence construction strategies. To address this, we introduce \textbf{ERSkill}, a retrieval-centric framework for evolving, skill-guided memory access. ERSkill compiles interaction histories into a structured memory store and represents retrieval behaviors as executable skills composed of fundamental primitives. At inference time, a trained router dynamically matches each query to a suitable retrieval skill to construct tailored evidence for answer generation. ERSkill co-evolves the skill set and the router during training. It employs an experience trie to efficiently record explored retrieval paths, alongside a double-frontier mechanism that separates oracle-side capability expansion from router-validated deployment. Experiments across multiple agent memory benchmarks demonstrate that ERSkill substantially outperforms strong non-evolving and evolving baselines. Notably, it improves the overall average across F1, BLEU-1, and LLM-judge scores by 31.3\% with Qwen3-Next-80B-A3B-Instruct and by 21.4\% with GPT-5.4-nano.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.12720 — 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 2026-10-19T04:13:06.696Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).