Pith Number

pith:D3EHK3FA

pith:2026:D3EHK3FAKT2IFQVUJBTQJC45WK

not attested not anchored not stored refs resolved

FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing

Erik Cambria, Haoran Luo, Mingda Zhang, Qika Lin, Rui Mao, Tiesunlong Shen, Wenjin Liu, Xiaoying Tang

A single agent can design complete agentic workflows end-to-end by making sequential edits to an executable canvas that supplies real-time syntax-checked feedback.

arxiv:2602.01664 v4 · 2026-02-02 · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{D3EHK3FAKT2IFQVUJBTQJC45WK}

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

Experimental results on twelve datasets show that FlowSteer significantly outperforms baselines across various tasks.

C2weakest assumption

That real-time syntax-checked execution feedback from the Workflow Canvas is sufficient to train a policy agent that can reliably repair errors during long-horizon workflow construction without external human guidance.

C3one line summary

A reinforcement learning policy agent designs executable agentic workflows by issuing atomic edits to a feedback-providing Workflow Canvas environment.

References

21 extracted · 21 resolved · 0 Pith anchors

[1] Greedy always picks largest coin≤N, which is locally optimal but not always globally optimal

[2] Greedy fails when using fewer large coins plus more medium coins yields fewer total coins (e.g., N=30: greedy=25+5×1=6 coins, optimal=3×10=3 coins)

[3] Dynamic programming guarantees finding the true minimum coin count

[4] The coin system {1,10,25} is NOT canonical (unlike {1,5,10,25} US coins), so greedy can fail. Plan:

[5] Implementgreedy_coins(n)that iteratively subtracts largest possible coin

Receipt and verification

First computed	2026-05-17T23:39:16.456876Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1ec8756ca054f482c2b44867048b9db2b3ff2c6935893b22ff762378c381dacc

Aliases

arxiv: 2602.01664 · arxiv_version: 2602.01664v4 · doi: 10.48550/arxiv.2602.01664 · pith_short_12: D3EHK3FAKT2I · pith_short_16: D3EHK3FAKT2IFQVU · pith_short_8: D3EHK3FA

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/D3EHK3FAKT2IFQVUJBTQJC45WK \
  | 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: 1ec8756ca054f482c2b44867048b9db2b3ff2c6935893b22ff762378c381dacc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5ebd31a8260a59d823164b2d97d01f3f54e8ac6edbd62761b4d7815a797a9872",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-02-02T05:30:42Z",
    "title_canon_sha256": "0817d5e021e1bf3cb926aaf87f4e894860bc8b29984b687d85ea6731d61e69e8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.01664",
    "kind": "arxiv",
    "version": 4
  }
}