Metraipolis › archive › dc_97f85c8e4eb5

SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation — arXiv:2609.03753

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03753
License (as archived)
CC0-1.0
Archived
2026-10-17T01:03:03.134Z
SHA-256 of the archived text
aad4e9c7978abfd899411d5f045a9748954fa19612950e0da7b95ef68b335547
Stable URL of this page
https://metraipolis.com/documento/dc_97f85c8e4eb5

How to cite

SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation — arXiv:2609.03753 — arXiv (en), https://arxiv.org/abs/2609.03753 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97f85c8e4eb5 (Metraipolis archive dc_97f85c8e4eb5, sha256 aad4e9c7978abfd899411d5f045a9748954fa19612950e0da7b95ef68b335547)
BibTeX
@misc{dc97f85c8e4eb5,
  title = {SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation — arXiv:2609.03753},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03753},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97f85c8e4eb5; sha256 aad4e9c7978abfd899411d5f045a9748954fa19612950e0da7b95ef68b335547},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03753. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cumulative culture enables humans to preserve, reuse, and extend knowledge and skills across experiences and generations. Inspired by this principle, we introduce \textit{SimSkill}, a self-evolving agent built around the Simulation of Urban MObility (SUMO) traffic simulator. SimSkill continually identifies capability gaps, generates and solves environment-grounded tasks, verifies solutions through an action--critic loop, and consolidates experience into episodic, procedural, and semantic memory. Through autonomous exploration, it builds a library of reusable skills and knowledge spanning major stages of the traffic-simulation workflow. We evaluate SimSkill on two held-out benchmarks across three backbone LLMs, with each result independently verified. It improves verified success by up to 25 percentage points, and ablations show complementary contributions from procedural and semantic memory. Its benefits remain backbone- and budget-dependent, as memory does not improve every model or uniformly reduce inference cost. More broadly, SimSkill illustrates a natural-language-centered design paradigm for LLM-based agent systems. Its high-level control logic, operating principles, and accumulated knowledge are expressed in natural language, while an LLM integrates them with executable tools and code to realize precise and reproducible execution. All code and experimental data are publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.03753 — 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 2026-10-17T00:22:10.235Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).