Pith Number

pith:M72AZJIE

pith:2023:M72AZJIEN5PWXGJF36E5H3QBUU

not attested not anchored not stored refs resolved

A Survey on Large Language Model based Autonomous Agents

Chen Ma, Hao Yang, Jiakai Tang, Jingsen Zhang, Ji-Rong Wen, Lei Wang, Wayne Xin Zhao, Xu Chen, Xueyang Feng, Yankai Lin, Zeyu Zhang, Zhewei Wei, Zhiyuan Chen

A unified framework organizes the construction of most LLM-based autonomous agents.

arxiv:2308.11432 v7 · 2023-08-22 · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{M72AZJIEN5PWXGJF36E5H3QBUU}

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 propose a unified framework that encompasses a majority of the previous work on LLM-based autonomous agents.

C2weakest assumption

That the proposed unified framework is sufficiently general to cover most existing LLM-agent architectures without major omissions or forced categorizations.

C3one line summary

A survey of LLM-based autonomous agents that proposes a unified framework for their construction and reviews applications in social science, natural science, and engineering along with evaluation methods and future directions.

References

185 extracted · 185 resolved · 37 Pith anchors

[1] Human-level control through deep reinforcement learning 2015

[2] Continuous control with deep reinforcement learning 2015 · arXiv:1509.02971

[3] Proximal Policy Optimization Algorithms 2017 · arXiv:1707.06347

[4] Soft actor- critic: O ff-policy maximum entropy deep reinforce- ment learning with a stochastic actor 2018

[5] Language models are few-shot learners 2020

Formal links

2 machine-checked theorem links

Cited by

34 papers in Pith

ClausewitzGPT Framework: A New Frontier in Theoretical Large Language Model Enhanced Information Operations

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools

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

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents

Receipt and verification

First computed	2026-05-17T23:38:53.598012Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

67f40ca5046f5f6b9925df89d3ee01a50a765fa95dfc20343001164b66bc4c06

Aliases

arxiv: 2308.11432 · arxiv_version: 2308.11432v7 · doi: 10.48550/arxiv.2308.11432 · pith_short_12: M72AZJIEN5PW · pith_short_16: M72AZJIEN5PWXGJF · pith_short_8: M72AZJIE

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/M72AZJIEN5PWXGJF36E5H3QBUU \
  | 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: 67f40ca5046f5f6b9925df89d3ee01a50a765fa95dfc20343001164b66bc4c06

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d7f43c299ee3303f9698e6ffd7c49aa94112a0baad9b968efc93b2a76f57678b",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2023-08-22T13:30:37Z",
    "title_canon_sha256": "6390fedb54a5a75ab078c0046ba1e2ac50958193170e92b0e74d1822201d7885"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2308.11432",
    "kind": "arxiv",
    "version": 7
  }
}