Pith Number

pith:25WBGP2Z

pith:2026:25WBGP2ZMRSKIU3HLKSPKKPYWM

not attested not anchored not stored refs pending

AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization

Choonghan Kim, Hangeol Chang, Hyunmin Hwang, Jaemin Kim, Jong Chul Ye

AgentPSO evolves multi-agent reasoning skills by treating each agent's natural-language description as a particle state that updates toward better performance.

arxiv:2605.08704 v2 · 2026-05-09 · 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{25WBGP2ZMRSKIU3HLKSPKKPYWM}

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

Experiments on mathematical and general reasoning benchmarks show that AgentPSO improves over static single-agent skills and test-time-only multi-agent reasoning baselines. The evolved skills further transfer across benchmarks and to another backbone model, suggesting that AgentPSO captures reusable reasoning procedures rather than merely optimizing benchmark-specific prompts.

C2weakest assumption

That iterative semantic updates to natural-language skill descriptions (combining previous velocity, personal-best, global-best, and self-reflective directions) produce genuine improvements in reasoning capability rather than superficial prompt changes, and that these updates can be performed without access to model internals or gradients.

C3one line summary

AgentPSO evolves reusable multi-agent reasoning skills via PSO-inspired natural-language updates, outperforming static agents and test-time multi-agent baselines on math and general reasoning tasks with cross-benchmark transfer.

Receipt and verification

First computed	2026-06-29T01:14:32.935834Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d76c133f596464a453675aa4f529f8b307378d45039b42e37489ef6aaf208545

Aliases

arxiv: 2605.08704 · arxiv_version: 2605.08704v2 · doi: 10.48550/arxiv.2605.08704 · pith_short_12: 25WBGP2ZMRSK · pith_short_16: 25WBGP2ZMRSKIU3H · pith_short_8: 25WBGP2Z

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/25WBGP2ZMRSKIU3HLKSPKKPYWM \
  | 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: d76c133f596464a453675aa4f529f8b307378d45039b42e37489ef6aaf208545

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "764ee388caa36a8ea2ba00acab82d8e4ca1d987c59a37c2a686e84d161d15c36",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-09T05:38:21Z",
    "title_canon_sha256": "d9390cff993b833a8bfb15699f2fd5a75150500adae69ead80bc3bebcff6fc8d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.08704",
    "kind": "arxiv",
    "version": 2
  }
}