pith. sign in
Pith Number

pith:GC25BJ5S

pith:2026:GC25BJ5S5KHZYVENIUQT2N6DXU
not attested not anchored not stored refs resolved

Multi-Agentic Approach for History Matching of Oil Reservoirs

Evgeny Burnaev, Linar Samigullin, Sergei Shumilin

PetroGraph deploys specialized LLM agents to automate history matching and reduce reservoir mismatch by 95 percent on SPE1, 69 percent on SPE9, and 13 percent on Norne.

arxiv:2605.15028 v1 · 2026-05-14 · cs.MA

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{GC25BJ5S5KHZYVENIUQT2N6DXU}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

PetroGraph reduces the mismatch by 95% on SPE1, 69% on SPE9, and 13% on Norne using weighted normalized root mean square error as the objective.

C2weakest assumption

That LLM agents can reliably generate valid ECLIPSE input decks, choose physically admissible parameters, and steer optimization without introducing systematic errors that the reported metrics fail to detect.

C3one line summary

PetroGraph is a multi-agent LLM system that automates reservoir history matching and reduces mismatch by 95% on SPE1, 69% on SPE9, and 13% on the Norne field model.

References

53 extracted · 53 resolved · 1 Pith anchors

[1] Samoil, S., Fare, C., Jordan, K. E. & Chen, Z. History matching reservoir models with many objective bayesian optimization. Appl. AI Lett.5, e99, DOI: https://doi.org/10.1002/ail2.99 (2024). https://o 2024 · doi:10.1002/ail2.99
[2] Oliver, D. S. & Chen, Y . Recent progress on reservoir history matching: a review.Comput. Geosci.15, 185–221, DOI: 10.1007/s10596-010-9194-2 (2011) 2011 · doi:10.1007/s10596-010-9194-2
[3] Chai, Z., Nwachukwu, A., Zagayevskiy, Y ., Amini, S. & Madasu, S. An integrated closed-loop solution to assisted history matching and field optimization with machine learning techniques.J. Petroleum S 2020 · doi:10.1016/j.petrol.2020.108204
[4] Jimenez-Romero, C., Yegenoglu, A. & Blum, C. Multi-agent systems powered by large language models: Applications in swarm intelligence.Front. Artif. Intell.8, DOI: 10.3389/frai.2025.1593017 (2025) 2025 · doi:10.3389/frai.2025.1593017
[5] A survey on LLM-based multi-agent sys- tem: Recent advances and new frontiers in application.arXiv preprint arXiv:2412.17481 2024
Receipt and verification
First computed 2026-05-17T23:38:54.612300Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

30b5d0a7b2ea8f9c548d45213d37c3bd3226d5fab01dbf09d09717f1d1942b96

Aliases

arxiv: 2605.15028 · arxiv_version: 2605.15028v1 · doi: 10.48550/arxiv.2605.15028 · pith_short_12: GC25BJ5S5KHZ · pith_short_16: GC25BJ5S5KHZYVEN · pith_short_8: GC25BJ5S
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/GC25BJ5S5KHZYVENIUQT2N6DXU \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 30b5d0a7b2ea8f9c548d45213d37c3bd3226d5fab01dbf09d09717f1d1942b96
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "ee9c68f2a592f17e10b103c77b782c8c9039c32ad564126e4272cc00a2a8f55c",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.MA",
    "submitted_at": "2026-05-14T16:25:51Z",
    "title_canon_sha256": "0d7a03d0a6b8fec59014dfd08a6d36f1acec14f7894a68b8fe3a3589ac61d970"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15028",
    "kind": "arxiv",
    "version": 1
  }
}