Pith Number

pith:AIAENHVD

pith:2022:AIAENHVDVOP3XAIACVKK4FJS4K

not attested not anchored not stored refs resolved

MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

Amnon Shashua, Barak Lenz, Dor Muhlgay, Ehud Karpas, Erez Schwartz, Gal Shachaf, Hofit Bata, Kevin Leyton-Brown, Moshe Tenenholtz, Nir Ratner, Noam Rozen, Omri Abend, Opher Lieber, Shai Shalev-Shwartz, Yoav Levine, Yoav Shoham, Yonatan Belinkov

MRKL systems combine large language models with external knowledge and discrete reasoning modules to address inherent LM limits.

arxiv:2205.00445 v1 · 2022-05-01 · cs.CL · 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{AIAENHVDVOP3XAIACVKK4FJS4K}

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

We define a flexible architecture with multiple neural models, complemented by discrete knowledge and reasoning modules.

C2weakest assumption

That the interfaces between neural language components and discrete knowledge/reasoning modules can be made reliable enough to deliver net gains over monolithic LMs without introducing new failure modes at the boundaries.

C3one line summary

MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.

References

23 extracted · 23 resolved · 8 Pith anchors

[1] Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K.BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingin Proceedings of the 2019 Conference of the North American Chapter of 2019

[2] Language Models are Few-Shot Learners 2005 · arXiv:2005.14165

[3] & Shoham, Y.Jurassic-1: Technical Details and Evaluation 2021 2021

[4] PaLM: Scaling Language Modeling with Pathways · arXiv:2204.02311

[5] et al.Exploring the Limits of Transfer Learning with a Uniﬁed Text- to-Text Transformer.Journal of Machine Learning Research21, 1–67 2020

Formal links

3 machine-checked theorem links

Cited by

27 papers in Pith

Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration

Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents

Interactive Evaluation Requires a Design Science

Receipt and verification

First computed	2026-05-17T23:38:53.129067Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0200469ea3ab9fbb81001554ae1532e29ddc4f9242c712921ba03609556d0f72

Aliases

arxiv: 2205.00445 · arxiv_version: 2205.00445v1 · doi: 10.48550/arxiv.2205.00445 · pith_short_12: AIAENHVDVOP3 · pith_short_16: AIAENHVDVOP3XAIA · pith_short_8: AIAENHVD

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/AIAENHVDVOP3XAIACVKK4FJS4K \
  | 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: 0200469ea3ab9fbb81001554ae1532e29ddc4f9242c712921ba03609556d0f72

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1999b508cf59abc1f097ea9dba4c11f02cf4b973f0f34fda729975ac53eaaa33",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2022-05-01T11:01:28Z",
    "title_canon_sha256": "18c647d28ce5d0ac2f31250b5c40afffc6fe0a93dc0516aeebe66669afb6e5cd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2205.00445",
    "kind": "arxiv",
    "version": 1
  }
}