Pith Number

pith:TYFQR5V6

pith:2026:TYFQR5V6WHUWY7MEVY4BI5UOMH

not attested not anchored not stored refs pending

Learning Without Losing Identity: Capability Evolution for Embodied Agents

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

Embodied agents improve task success from 32% to 91% by evolving separate capability modules without altering their core identity or safety limits.

arxiv:2604.07799 v2 · 2026-04-09 · cs.RO · 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{TYFQR5V6WHUWY7MEVY4BI5UOMH}

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 demonstrate through simulated embodied tasks that capability evolution improves task success rates from 32.4% to 91.3% over 20 iterations, outperforming both agent-modification baselines and established skill-learning methods (SPiRL, SkiMo), while preserving zero policy drift and zero safety violations.

C2weakest assumption

That embodied capabilities can be cleanly decomposed into independent, versioned ECMs whose evolution leaves the persistent agent identity and safety constraints untouched.

C3one line summary

Embodied agents maintain a persistent identity while evolving capabilities via modular ECMs, raising simulated task success from 32.4% to 91.3% over 20 iterations with zero policy drift or safety violations.

Cited by

6 papers in Pith

Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution

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	2026-05-22T01:04:01.806262Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9e0b08f6beb1e96c7d84ae3814768e61d3a02edba71c2468a6fec879ce5bc29f

Aliases

arxiv: 2604.07799 · arxiv_version: 2604.07799v2 · doi: 10.48550/arxiv.2604.07799 · pith_short_12: TYFQR5V6WHUW · pith_short_16: TYFQR5V6WHUWY7ME · pith_short_8: TYFQR5V6

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/TYFQR5V6WHUWY7MEVY4BI5UOMH \
  | 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: 9e0b08f6beb1e96c7d84ae3814768e61d3a02edba71c2468a6fec879ce5bc29f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "aa37fea55ebea829264347c29b1a406e5cc205bb475d8e924e771860c3ee6b40",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-04-09T04:51:07Z",
    "title_canon_sha256": "3edf72d21b37be9a9c8d7643d80b8ae9c709a7060d82aa981eb6286ba6f8a37e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.07799",
    "kind": "arxiv",
    "version": 2
  }
}