Pith Number

pith:656DEUNA

pith:2023:656DEUNACXYL43CYGYJA4Y6JXK

not attested not anchored not stored refs resolved

Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

Rui Wang, Shuming Shi, Tian Liang, Wenxiang Jiao, Xing Wang, Yan Wang, Yujiu Yang, Zhaopeng Tu, Zhiwei He

Large language models overcome stuck reasoning by having multiple agents argue tit-for-tat under a judge instead of reflecting alone.

arxiv:2305.19118 v4 · 2023-05-30 · 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{656DEUNACXYL43CYGYJA4Y6JXK}

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

Our MAD framework encourages divergent thinking in LLMs which would be helpful for tasks that require deep levels of contemplation. Experiment results on two challenging datasets, commonsense machine translation and counter-intuitive arithmetic reasoning, demonstrate the effectiveness of our MAD framework.

C2weakest assumption

That a judge LLM can fairly evaluate and synthesize the debate without inheriting the same Degeneration-of-Thought bias, and that the tit-for-tat dynamic reliably produces novel thoughts rather than escalating errors.

C3one line summary

Multi-agent debate with tit-for-tat arguments and a judge LLM improves reasoning by preventing LLMs from locking into incorrect initial solutions.

References

286 extracted · 286 resolved · 10 Pith anchors

[1] Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages= 2023

[3] A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity , author=. Proceedings of the 13th International Joint Conference on Natural Language Process

[7] Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing , pages= 2015

[12] Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology , pages=

[13] Advances in neural information processing systems , volume=

Formal links

2 machine-checked theorem links

Cited by

47 papers in Pith

How Far Are We from Generating Missing Modalities with Foundation Models?

A Survey on LLM-as-a-Judge

Large Language Model Agent: A Survey on Methodology, Applications and Challenges

A Survey of Scaling in Large Language Model Reasoning

QM-ToT: A Medical Tree of Thoughts Reasoning Framework for Quantized Model

Receipt and verification

First computed	2026-05-18T03:30:52.354097Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f77c3251a015f0be6c5836120e63c9ba9c42f0af9f480f7a1fb7885929e16031

Aliases

arxiv: 2305.19118 · arxiv_version: 2305.19118v4 · doi: 10.48550/arxiv.2305.19118 · pith_short_12: 656DEUNACXYL · pith_short_16: 656DEUNACXYL43CY · pith_short_8: 656DEUNA

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/656DEUNACXYL43CYGYJA4Y6JXK \
  | 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: f77c3251a015f0be6c5836120e63c9ba9c42f0af9f480f7a1fb7885929e16031

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "536774355440d16d32852d1d5b7dbfec57261204744c37a7e2a685e9e8d8360d",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-05-30T15:25:45Z",
    "title_canon_sha256": "314e98a7f73c2b0c1bc6afb2a80a822404b6a592830fef72602665def411d52f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.19118",
    "kind": "arxiv",
    "version": 4
  }
}