Pith Number

pith:EOLHNYZR

pith:2026:EOLHNYZROGPKAYAZNYAAAPIBN6

not attested not anchored not stored refs pending

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents

Haifeng Zhang, Haoxuan Li, Jun Wang, Mengyue Yang, Qirui Mi, Yisen Wang, Zhijian Ma

Skill-Pro lets LLM agents learn reusable procedural skills from past experiences without updating any parameters.

arxiv:2602.01869 v3 · 2026-02-02 · 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{EOLHNYZROGPKAYAZNYAAAPIBN6}

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

Skill-Pro achieves superior reuse rates and significant performance gains with extreme memory compression by autonomously learning reusable procedural skills from interaction experiences without parameter updates, using Skill-MDP formalization and Non-Parametric PPO for reliable verification.

C2weakest assumption

That semantic gradients combined with a PPO Gate can generate and verify high-quality skills that remain executable and non-degrading across recurring scenarios without any post-hoc exclusions or capability loss.

C3one line summary

Skill-Pro enables LLM agents to autonomously learn, verify, and reuse compact procedural skills from experience via a Skill-MDP formalization and Non-Parametric PPO, yielding higher reuse rates, performance gains, and extreme memory compression across in-domain, cross-task, and cross-agent settings.

Cited by

26 papers in Pith

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

Metis: Bridging Text and Code Memory for Self-Evolving Agents

PreAct: Computer-Using Agents that Get Faster on Repeated Tasks

Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents

SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior

Receipt and verification

First computed	2026-05-29T02:05:40.216021Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

239676e331719ea060196e00003d016f82e0522ee7e3604846dd9ff2c7445ab2

Aliases

arxiv: 2602.01869 · arxiv_version: 2602.01869v3 · doi: 10.48550/arxiv.2602.01869 · pith_short_12: EOLHNYZROGPK · pith_short_16: EOLHNYZROGPKAYAZ · pith_short_8: EOLHNYZR

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/EOLHNYZROGPKAYAZNYAAAPIBN6 \
  | 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: 239676e331719ea060196e00003d016f82e0522ee7e3604846dd9ff2c7445ab2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "090d34ac9a4679279642127a2cbb9daaa4c455584eeaf648ab6633dacac456bc",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-02-02T09:43:12Z",
    "title_canon_sha256": "9ce1cd3f78023a14abbe6a6e7c1681d1c7ddec483468097ab271327fdc2adcd2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.01869",
    "kind": "arxiv",
    "version": 3
  }
}