Pith Number

pith:YQRW5RPB

pith:2026:YQRW5RPBUVOSA5XPEWRUZNEJQF

not attested not anchored not stored refs resolved

MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters

C. Bash, D. Milojicic, H. Moore, S. Pasricha, S. Qi

MARLIN uses multi-agent game-theoretic reinforcement learning to cut TTFT by 18 percent, carbon emissions by 33 percent, water usage by 43 percent, and energy costs by 11 percent for LLM inference in cloud datacenters.

arxiv:2605.13496 v1 · 2026-05-13 · cs.DC · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YQRW5RPBUVOSA5XPEWRUZNEJQF}

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

MARLIN demonstrates a reduction of at least 18% in TTFT, 33% in carbon emissions, 43% in water usage, and 11% in energy costs compared to state-of-the-art LLM inference management frameworks.

C2weakest assumption

That the simulation environment and workload traces used to train and evaluate the multi-agent system accurately capture the dynamics, constraints, and measurement noise of real cloud datacenters running production LLM inference.

C3one line summary

MARLIN applies multi-agent game-theoretic RL to cut TTFT by at least 18%, carbon emissions by 33%, water usage by 43%, and energy costs by 11% versus prior LLM inference managers.

References

36 extracted · 36 resolved · 0 Pith anchors

[1] Llm statistics 2026: Comprehensive insights into market trends and integration, 2026

[2] Chatgpt users statistics (2026) – active users & global growth data, 2026

[3] Accessed on Mar.31.2026 2026

[4] The unseen ai disruptions for power grids: Llm-induced transients, 2024

[5] What we know about energy use at u.s. data centers amid the ai boom, 2026

Receipt and verification

First computed	2026-05-18T02:44:41.086776Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c4236ec5e1a55d2076ef25a34cb489815d5fa097985dd940b98164510df697ed

Aliases

arxiv: 2605.13496 · arxiv_version: 2605.13496v1 · doi: 10.48550/arxiv.2605.13496 · pith_short_12: YQRW5RPBUVOS · pith_short_16: YQRW5RPBUVOSA5XP · pith_short_8: YQRW5RPB

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF \
  | 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: c4236ec5e1a55d2076ef25a34cb489815d5fa097985dd940b98164510df697ed

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c9e4b4e3c75af6f561928af8cadae91f0b3ae0adb12844f51d8e96816581d0a6",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.DC",
    "submitted_at": "2026-05-13T13:20:02Z",
    "title_canon_sha256": "7b948215a9cacc432ed7028ed0cc036a64f19dfc66239cd8c4a12ab5b580b0f8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13496",
    "kind": "arxiv",
    "version": 1
  }
}