Pith Number

pith:35NLMLU3

pith:2026:35NLMLU3DQE5UGZACVNSCCAFQW

not attested not anchored not stored refs resolved

AgenticAITA: A Proof-Of-Concept About Deliberative Multi-Agent Reasoning for Autonomous Trading Systems

Ivan Letteri

Multiple off-the-shelf language models can autonomously analyze markets, negotiate risks, and execute trades through a structured deliberative loop without any training or human input.

arxiv:2605.12532 v1 · 2026-05-01 · q-fin.TR · cs.AI · stat.ME

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{35NLMLU3DQE5UGZACVNSCCAFQW}

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

Validated over a five-day autonomous dry-run session under live market conditions, the framework demonstrates operational correctness of the deliberative pipeline, achieving 157 zero-intervention invocations across 76 assets with an 11.5% agentic friction rate that confirms non-trivial inter-agent negotiation.

C2weakest assumption

That off-the-shelf large language models can reliably perform the roles of financial analyst, risk manager, and executor through natural language reasoning and typed JSON contracts without any domain-specific training or fine-tuning.

C3one line summary

AgenticAITA proposes a training-free multi-agent LLM framework for autonomous trading using a deliberative pipeline, Z-score triggers, and safety gates, shown to run correctly in a five-day live dry-run with 157 invocations.

References

28 extracted · 28 resolved · 1 Pith anchors

[1] Statistical Arbitrage V olatility-Driven with Statistics and Machine Learning Models for Stock Market Forecasting.SN Computer Science, 6:918, 2025 2025

[2] Trading Strategy Validation Using Forwardtesting with Deep Neural Networks: 2023

[3] Dnn-forwardtesting: A new trading strategy validation using statistical timeseries analysis and deep neural networks, 2022 2022

[4] A comparative analysis of statistical and machine learning models for outlier detection in bitcoin limit order books, 2025 2025

[5] V olts: A volatility-based trading system to forecast stock markets trend using statistics and machine learning, 2023 2023

Receipt and verification

First computed	2026-05-18T03:10:02.559665Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

df5ab62e9b1c09da1b20155b21080585aebb244cac98fc59a065682183f2f5c1

Aliases

arxiv: 2605.12532 · arxiv_version: 2605.12532v1 · doi: 10.48550/arxiv.2605.12532 · pith_short_12: 35NLMLU3DQE5 · pith_short_16: 35NLMLU3DQE5UGZA · pith_short_8: 35NLMLU3

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/35NLMLU3DQE5UGZACVNSCCAFQW \
  | 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: df5ab62e9b1c09da1b20155b21080585aebb244cac98fc59a065682183f2f5c1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5d92526177b188ad4678ca5a994006c5ff2de74cd10a36abee1fe74f80a47603",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ME"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "q-fin.TR",
    "submitted_at": "2026-05-01T16:25:43Z",
    "title_canon_sha256": "9550b6d030a3a904bbc4ecb97c45d1c8fbb31ce1413b2898be39743d478ad4b0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12532",
    "kind": "arxiv",
    "version": 1
  }
}