Pith Number

pith:NBARWHG3

pith:2026:NBARWHG3EU57YN3KXUPZ6Q4AU4

not attested not anchored not stored refs resolved

DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery

Tianyu Liu, Wengong Jin, Xiwei Cheng, Yikun Zhang, Yuanqi Du

A self-evolving agent reuses cross-task memory to reach state-of-the-art drug discovery models with little or no new search.

arxiv:2605.15461 v1 · 2026-05-14 · cs.LG · 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{NBARWHG3EU57YN3KXUPZ6Q4AU4}

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

In 33 molecular property prediction tasks, DrugSAGE ranks first among nine SOTA agents in a single-task setting. With memory accumulated from 16 smaller tasks, DrugSAGE achieves an averaged normalized score of 0.935 on 17 held-out tasks in a cross-task evaluation setting and outperforms all baseline agents by 10-30% in a zero-test-time search regime.

C2weakest assumption

The cross-task memory of verified skills, statistical evidence about strategies, and records of errors and fixes can be transferred effectively to new molecular property prediction tasks without introducing harmful biases or performance drops due to differences in task distributions.

C3one line summary

DrugSAGE accumulates cross-task memory of skills, statistical evidence, and recurring errors to let LLM agents achieve top-ranked performance on molecular property prediction tasks with reduced or zero test-time search.

References

69 extracted · 69 resolved · 6 Pith anchors

[1] Under review 2025

[2] Biomni: A general-purpose biomedical ai agent 2025

[3] John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, et al 2025

[4] autoresearch: Ai agents running research on single-gpu nanochat training automatically.https://github.com/karpathy/autoresearch, 2026 2026

[5] Gonzalez, and Ion Stoica 2018 · arXiv:1807.05118

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T00:00:59.778889Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

68411b1cdb253bfc376abd1f9f4380a70f0d2f09599213de499f271820ef7e82

Aliases

arxiv: 2605.15461 · arxiv_version: 2605.15461v1 · doi: 10.48550/arxiv.2605.15461 · pith_short_12: NBARWHG3EU57 · pith_short_16: NBARWHG3EU57YN3K · pith_short_8: NBARWHG3

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/NBARWHG3EU57YN3KXUPZ6Q4AU4 \
  | 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: 68411b1cdb253bfc376abd1f9f4380a70f0d2f09599213de499f271820ef7e82

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "950379f08bc1a36b0e882b0c7bac0f17114b1742f4d411da2ede010664cbf949",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T22:49:42Z",
    "title_canon_sha256": "a6d93902a790536e381f465d6599a3bf0614ac23950073fada92a220c9ddc597"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15461",
    "kind": "arxiv",
    "version": 1
  }
}