Metraipolis › archive › dc_e24ce4d65010

MarkovSim: an LLM Agent Harness with Bounded Context for Long-Horizon Computational Simulation — arXiv:2610.35349

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.35349
License (as archived)
CC0-1.0
Archived
2026-10-27T08:02:41.062Z
SHA-256 of the archived text
63fc4e6001e76e44f3571d8f990ffd64f5c5837a326b8604eb689008e07e8063
Stable URL of this page
https://metraipolis.com/documento/dc_e24ce4d65010

How to cite

MarkovSim: an LLM Agent Harness with Bounded Context for Long-Horizon Computational Simulation — arXiv:2610.35349 — arXiv (en), https://arxiv.org/abs/2610.35349 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e24ce4d65010 (Metraipolis archive dc_e24ce4d65010, sha256 63fc4e6001e76e44f3571d8f990ffd64f5c5837a326b8604eb689008e07e8063)
BibTeX
@misc{dce24ce4d65010,
  title = {MarkovSim: an LLM Agent Harness with Bounded Context for Long-Horizon Computational Simulation — arXiv:2610.35349},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.35349},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e24ce4d65010; sha256 63fc4e6001e76e44f3571d8f990ffd64f5c5837a326b8604eb689008e07e8063},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35349. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent studies have applied large language model (LLM) agent systems to computational simulation workflows. Such workflows are long-horizon, so the information generated can exceed what an LLM can reason over at once, its context window. Context management is therefore essential, yet existing systems have either neglected it or treated it as a supporting mechanism rather than a subject of study. This paper presents MarkovSim, an LLM agent harness for long-horizon computational simulation, whose core is a context management scheme built into the workflow. The workflow record is written to a memory system with a predefined schema, and at workflow-defined boundaries, namely the state transitions of a finite-state machine a compact representation of the solution progress is constructed from it as the agent's context. Instantiated on finite element analysis and evaluated on six benchmark problems, MarkovSim passed 16 of 18 runs and corrected its own faults in both the solver operations and the model physics. The engineer was consulted only where engineering judgement was needed. The context remained bounded throughout every run, regardless of its length.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computational Engineering, Finance, and Science (cs.CE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.35349 — 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 2026-10-27T07:55:30.985Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).