Pith Number

pith:4K5LTY6D

pith:2026:4K5LTY6DUMKYSOYV6E37L6DU4U

not attested not anchored not stored refs resolved

GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources

Boning Huangfu, Boxiao Du, Chen Chen, Minchen Yu, Minyi Guo, Xiaoyi Fan, Yizhou Luo, Zijun Li

GoodServe routes agentic LLM requests across heterogeneous GPUs with predict-and-rectify decisions to raise goodput.

arxiv:2605.16867 v1 · 2026-05-16 · cs.DC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{4K5LTY6DUMKYSOYV6E37L6DU4U}

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

Our evaluations show that GoodServe improves goodput by up to 27.4% over existing routing methods.

C2weakest assumption

That the estimates of request output lengths as well as the GPU serving status can be done in an accurate and also practical manner.

C3one line summary

GoodServe proposes a predict-and-rectify routing system for agentic LLM inferences on heterogeneous GPUs that improves goodput by up to 27.4%.

References

40 extracted · 40 resolved · 9 Pith anchors

[1] Efficient and scalable agentic ai with heteroge- neous systems.arXiv preprint arXiv:2507.19635, 2025 2025

[2] Ai-powered chat agent: Revolutionizing online shopping 2024

[3] Optimal scheduling algorithms for llm inference: Theory and practice.Proceedings of the ACM on Measurement and Analysis of Computing Systems, 9(3):1–43, 2025 2025

[4] LiteLLM: Python sdk and proxy server for unified llm api access 2026

[5] Slice: Slo-driven scheduling for llm inference on edge computing devices.arXiv preprint arXiv:2510.18544, 2025 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:27.275821Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e2bab9e3c3a315893b15f137f5f874e53fd8b3089a2e38fef5a07010396a791e

Aliases

arxiv: 2605.16867 · arxiv_version: 2605.16867v1 · doi: 10.48550/arxiv.2605.16867 · pith_short_12: 4K5LTY6DUMKY · pith_short_16: 4K5LTY6DUMKYSOYV · pith_short_8: 4K5LTY6D

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/4K5LTY6DUMKYSOYV6E37L6DU4U \
  | 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: e2bab9e3c3a315893b15f137f5f874e53fd8b3089a2e38fef5a07010396a791e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9de61d8f61c93516055d2ec1b9f28f405fe1bacae8fb0d28683207dfbd3ca34b",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.DC",
    "submitted_at": "2026-05-16T08:01:12Z",
    "title_canon_sha256": "b88b84142799998f4d98141799b484dfbc48440cdb0ac02ba1bd43f9394ce499"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16867",
    "kind": "arxiv",
    "version": 1
  }
}