Pith Number

pith:24LDJL2T

pith:2026:24LDJL2TQ3M2O2CAASH362AG57

not attested not anchored not stored refs pending

RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement

Abhay Venkatesh, Brendan Evers, Sam Saltwick, Will LeVine

RubricRefine generates task-specific rubrics to score and repair tool-use code for contract violations before any execution occurs.

arxiv:2605.09730 v3 · 2026-05-10 · cs.LG · cs.SE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{24LDJL2TQ3M2O2CAASH362AG57}

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

With zero execution attempts, RubricRefine reaches 0.86 on M3ToolEval averaged across seven models-improving over prior inference-time baselines on every model tested on this benchmark, at 2.6X lower latency than the strongest non-iterative alternative.

C2weakest assumption

That inter-tool contract violations (wrong output shape, incorrect routing, broken argument provenance) are the dominant failures and that automatically generated rubrics can reliably detect them without any execution feedback or model-specific tuning.

C3one line summary

RubricRefine improves tool-use agent reliability to 0.86 on M3ToolEval by generating rubrics for pre-execution contract checking and iterative repair, outperforming baselines at 2.6X lower latency while showing no gain on single-step tasks.

Cited by

1 paper in Pith

Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

Receipt and verification

First computed	2026-05-20T00:02:12.784330Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d71634af5386d9a76840048fbf6806efd7f792b4d4c5c15d26dc2bd2c693b728

Aliases

arxiv: 2605.09730 · arxiv_version: 2605.09730v3 · doi: 10.48550/arxiv.2605.09730 · pith_short_12: 24LDJL2TQ3M2 · pith_short_16: 24LDJL2TQ3M2O2CA · pith_short_8: 24LDJL2T

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/24LDJL2TQ3M2O2CAASH362AG57 \
  | 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: d71634af5386d9a76840048fbf6806efd7f792b4d4c5c15d26dc2bd2c693b728

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d8622bcaec8443429806e5c6c1146b1770b27141eabf9be38eb837912bb07ce9",
    "cross_cats_sorted": [
      "cs.SE"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-10T19:57:32Z",
    "title_canon_sha256": "ccf23749a1292b2dbad90ba1feda00214e8796edd66e17274099458699cf2c6e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.09730",
    "kind": "arxiv",
    "version": 3
  }
}