Pith Number

pith:RMQ3FXPQ

pith:2026:RMQ3FXPQU3CWNAMUZUGC76YHVD

not attested not anchored not stored refs pending

Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution

Cong Yang, John See, Simin Luan, Xue Qin, Zhijun Li

Embodied agents achieve reliable policy compliance when cognition is separated from an external runtime governance layer.

arxiv:2604.07833 v3 · 2026-04-09 · cs.RO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{RMQ3FXPQU3CWNAMUZUGC76YHVD}

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

We formalize the control boundary among the embodied agent, Embodied Capability Modules (ECMs), and runtime governance layer, and validate through 1000 randomized simulation trials across three governance dimensions. Results show 96.2% interception of unauthorized actions, reduction of unsafe continuation from 100% to 22.2% under runtime drift, and 91.4% recovery success with full policy compliance, substantially outperforming all baselines (p<0.001).

C2weakest assumption

The simulation trials accurately model real-world policy violations, runtime drift, and recovery scenarios for embodied agents; the proposed governance layer can be implemented efficiently in actual hardware and software systems without introducing new vulnerabilities.

C3one line summary

A runtime governance framework for embodied agents achieves 96.2% interception of unauthorized actions and 91.4% recovery success in 1000 simulation trials by externalizing policy enforcement.

Formal links

1 machine-checked theorem link

Cited by

4 papers in Pith

Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation

EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems

Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation

ECM Contracts: Contract-Aware, Versioned, and Governable Capability Interfaces for Embodied Agents

Receipt and verification

First computed	2026-05-22T01:04:01.852697Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8b21b2ddf0a6c5668194cd0c2ffb07a8e612f0b76fc99061b89b45e38613e997

Aliases

arxiv: 2604.07833 · arxiv_version: 2604.07833v3 · doi: 10.48550/arxiv.2604.07833 · pith_short_12: RMQ3FXPQU3CW · pith_short_16: RMQ3FXPQU3CWNAMU · pith_short_8: RMQ3FXPQ

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/RMQ3FXPQU3CWNAMUZUGC76YHVD \
  | 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: 8b21b2ddf0a6c5668194cd0c2ffb07a8e612f0b76fc99061b89b45e38613e997

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "cbff7f958ed55dcc6ffa5318d98e383cf5b3731da9b269147aea3ca8c45f637e",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-04-09T05:35:08Z",
    "title_canon_sha256": "90ae81df94f5a5e9bc40546426b1acbb6ebdb9b4658a98ca60c1b6cd677e771b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.07833",
    "kind": "arxiv",
    "version": 3
  }
}