Pith Number

pith:J276MSRK

pith:2026:J276MSRKZYZD4E7PELII3T7AEU

not attested not anchored not stored refs resolved

SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch

Zhantao Wang

SDOF models multi-agent orchestration as a constrained state machine to let a 7B router beat zero-shot GPT-4o on adversarial routing while blocking all illegal operations.

arxiv:2605.15204 v1 · 2026-04-20 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{J276MSRKZYZD4E7PELII3T7AEU}

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 GSPO-aligned 7B Intent Router achieves higher joint accuracy than zero-shot GPT-4o on this FSM-constrained adversarial routing benchmark (80.9% versus 48.9%). In end-to-end execution, SDOF reaches 86.5% task completion and blocks all 22 operations in the injection, illegal HR subset.

C2weakest assumption

The expert-curated 185 scenarios and the Beisen iTalent platform data accurately represent general multi-agent orchestration challenges and that the GoalStage finite-automaton mapping faithfully captures real business process constraints without missing edge cases.

C3one line summary

SDOF combines an RLHF-trained intent router with a state-aware dispatcher using finite automata to constrain multi-agent orchestration, reporting 80.9% routing accuracy and 86.5% task completion on a recruitment platform while blocking unsafe actions.

References

25 extracted · 25 resolved · 4 Pith anchors

[1] AgentAuditor: Safety and security evaluation for large language model agents 2025

[2] Langchain: Building applications with LLMs through composability.https://github 2023

[3] AgentVerse: Facilitating multi-agent collaboration and exploring emergent be- haviors 2024

[4] Cooperative AI: machines must learn to find common ground 2021

[5] Agentscope: A flexible yet robust multi-agent platform 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:45.900309Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4ebfe64a2ace323e13ef22d08dcfe0253f2625ccb9655806abfe5d41eedbda61

Aliases

arxiv: 2605.15204 · arxiv_version: 2605.15204v1 · doi: 10.48550/arxiv.2605.15204 · pith_short_12: J276MSRKZYZD · pith_short_16: J276MSRKZYZD4E7P · pith_short_8: J276MSRK

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/J276MSRKZYZD4E7PELII3T7AEU \
  | 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: 4ebfe64a2ace323e13ef22d08dcfe0253f2625ccb9655806abfe5d41eedbda61

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "98f1b1c82e3214113f2157c03416f5a2de529c2313ac5a3a7cfab68915a87ca1",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-20T12:51:39Z",
    "title_canon_sha256": "2682461e28eb2548ba4359aad730a8d194755abb6fe559087bb241894b3a8491"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15204",
    "kind": "arxiv",
    "version": 1
  }
}