Pith Number

pith:EFGOQGWQ

pith:2023:EFGOQGWQBVIWVZWNPFASUUA6RN

not attested not anchored not stored refs resolved

Cognitive Architectures for Language Agents

Karthik Narasimhan, Shunyu Yao, Theodore R. Sumers, Thomas L. Griffiths

CoALA structures language agents with modular memory components, a structured action space, and a generalized decision-making process drawn from cognitive science.

arxiv:2309.02427 v3 · 2023-09-05 · cs.AI · cs.CL · cs.LG · cs.SC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EFGOQGWQBVIWVZWNPFASUUA6RN}

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

CoALA describes a language agent with modular memory components, a structured action space to interact with internal memory and external environments, and a generalized decision-making process to choose actions.

C2weakest assumption

That principles from cognitive science and symbolic AI can be directly transferred to LLM-based agents without major adaptation or loss of the benefits that make LLMs effective in the first place.

C3one line summary

CoALA is a modular cognitive architecture for language agents that organizes memory components, action spaces for internal and external interaction, and a generalized decision-making loop to support more systematic development of capable agents.

References

96 extracted · 96 resolved · 45 Pith anchors

[1] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances · arXiv:2204.01691

[2] J. Andreas. Language models as agent models. InFindings of the Association for Computational Linguistics: EMNLP 2022, pages 5769–5779, 2022

[3] 19 Published in Transactions on Machine Learning Research (02/2024) A. D. Baddeley and G. Hitch. Working memory. InPsychology of Learning and Motivation, volume 8, pages 47–89. Elsevier, 2024

[4] Constitutional AI: Harmlessness from AI Feedback · arXiv:2212.08073

[5] Z., Rae, J., Wierstra, D., and Hass- abis, D · arXiv:1606.04460

Formal links

3 machine-checked theorem links

Cited by

26 papers in Pith

MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis

Mem-$\pi$: Adaptive Memory through Learning When and What to Generate

Receipt and verification

First computed	2026-05-17T23:38:46.832897Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

214ce81ad00d516ae6cd79412a501e8b71f2b5e54e2a48340ccaaf634396e86e

Aliases

arxiv: 2309.02427 · arxiv_version: 2309.02427v3 · doi: 10.48550/arxiv.2309.02427 · pith_short_12: EFGOQGWQBVIW · pith_short_16: EFGOQGWQBVIWVZWN · pith_short_8: EFGOQGWQ

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/EFGOQGWQBVIWVZWNPFASUUA6RN \
  | 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: 214ce81ad00d516ae6cd79412a501e8b71f2b5e54e2a48340ccaaf634396e86e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "86d0b6bd5b1490ba081f23a157aff529ac85d432f794093827d5fc65e05eba9e",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG",
      "cs.SC"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2023-09-05T17:56:20Z",
    "title_canon_sha256": "8a85a0b59f7d58386b473f0e0ff4571994e49864b784d3967212a867e6a17fbd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2309.02427",
    "kind": "arxiv",
    "version": 3
  }
}