Pith Number

pith:WFKUFZ5S

pith:2026:WFKUFZ5SZI3EHXDFXVT3S6V45L

not attested not anchored not stored refs pending

Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

Hong Cheng, Junhao Shen, Teng Zhang, Xiaoyan Zhao

Agentic RL agents improve when the active external skill set is treated as a dynamic optimization variable updated jointly with policy learning.

arxiv:2605.10923 v2 · 2026-05-11 · cs.LG · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WFKUFZ5SZI3EHXDFXVT3S6V45L}

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

SLIM treats the active external skill set as a dynamic optimization variable jointly updated with policy learning. Experiments show that SLIM outperforms the best baselines by an average of 7.1% points across ALFWorld and SearchQA. Results further indicate that policy learning and external skill retention are not mutually exclusive.

C2weakest assumption

The assumption that the optimal active skill set is non-monotonic, task- and stage-dependent, and that leave-one-skill-out validation can reliably estimate each skill's marginal external contribution without introducing bias or prohibitive cost.

C3one line summary

SLIM dynamically optimizes active external skills in agentic RL via leave-one-skill-out marginal contribution estimates and three lifecycle operations, outperforming baselines by 7.1% on ALFWorld and SearchQA while showing some skills are internalized and others remain external.

Receipt and verification

First computed	2026-05-20T00:03:17.205903Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b15542e7b2ca3643dc65bd67b97abceadc7fb1324703cc5520728d550027df9c

Aliases

arxiv: 2605.10923 · arxiv_version: 2605.10923v2 · doi: 10.48550/arxiv.2605.10923 · pith_short_12: WFKUFZ5SZI3E · pith_short_16: WFKUFZ5SZI3EHXDF · pith_short_8: WFKUFZ5S

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/WFKUFZ5SZI3EHXDFXVT3S6V45L \
  | 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: b15542e7b2ca3643dc65bd67b97abceadc7fb1324703cc5520728d550027df9c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0692e3c7bb8b97307acea2c1132cff40a11070e0fe5fcfa8c4e9a46cdc7ac99b",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-11T17:55:13Z",
    "title_canon_sha256": "763b92c85adc2aae4ad8ace05bd5d0aa631e4527c6023334dec339fd4c2c40b2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.10923",
    "kind": "arxiv",
    "version": 2
  }
}