Pith Number

pith:XS6AJHG4

pith:2026:XS6AJHG4BXG7KVMFAMNXHXIIOM

not attested not anchored not stored refs resolved

Polaris: A G\"odel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

Aditya Kakade, Shirish Karande, Vivek Srivastava

A 7B model improves its policy on unseen reasoning tasks by abstracting failures into compact reusable code patches.

arxiv:2603.23129 v2 · 2026-03-24 · 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{XS6AJHG4BXG7KVMFAMNXHXIIOM}

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

On MGSM, DROP, GPQA, and LitBench, a 7-billion-parameter model equipped with Polaris achieves consistent gains over the base policy and competitive baselines.

C2weakest assumption

That experience abstraction reliably produces compact strategies that transfer to unseen instances and that the minimal code patches improve performance without introducing regressions on other tasks.

C3one line summary

Polaris enables small LLMs to achieve recursive self-improvement by abstracting failure experiences into reusable policy patches that transfer across benchmark instances.

References

13 extracted · 13 resolved · 0 Pith anchors

[1] Examine how the policy’s logic or structure caused the error

[2] Step-by-step suggestions on how the policy could be revised to solve the task

[3] ‘python <code patch here> 2018

[4] role": "user 1999

[5] Continue to interact with the environment by executing actions based on the current analysis

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:15.697357Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bcbc049cdc0dcdf55585031b73dd087337a17c718f6e2b68c36875aa4e2d8afb

Aliases

arxiv: 2603.23129 · arxiv_version: 2603.23129v2 · doi: 10.48550/arxiv.2603.23129 · pith_short_12: XS6AJHG4BXG7 · pith_short_16: XS6AJHG4BXG7KVMF · pith_short_8: XS6AJHG4

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/XS6AJHG4BXG7KVMFAMNXHXIIOM \
  | 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: bcbc049cdc0dcdf55585031b73dd087337a17c718f6e2b68c36875aa4e2d8afb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "968f7d10425dd6630520ad2d9ae3ab6510a696a79e4a0cc300db3b0d7f047e89",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-03-24T12:25:32Z",
    "title_canon_sha256": "2cdf28ce9688ee3ffb8b65d47380449d94d37c3eb935fa991eec2fc33130ee62"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.23129",
    "kind": "arxiv",
    "version": 2
  }
}