Pith Number

pith:FECGQRX6

pith:2024:FECGQRX6RDAS532D4LSBA6OMVJ

not attested not anchored not stored refs resolved

Mixture-of-Agents Enhances Large Language Model Capabilities

Ben Athiwaratkun, Ce Zhang, James Zou, Jue Wang, Junlin Wang

A layered mixture of multiple LLM agents outperforms GPT-4 Omni on AlpacaEval 2.0, MT-Bench, and FLASK by using prior-layer outputs as auxiliary context.

arxiv:2406.04692 v1 · 2024-06-07 · cs.CL

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

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

MoA models achieves state-of-art performance on AlpacaEval 2.0, MT-Bench and FLASK, surpassing GPT-4 Omni. For example, our MoA using only open-source LLMs is the leader of AlpacaEval 2.0 by a substantial gap, achieving a score of 65.1% compared to 57.5% by GPT-4 Omni.

C2weakest assumption

That feeding previous-layer outputs as auxiliary information to each agent will reliably improve response quality without introducing noise or compounding errors from weaker models in the ensemble.

C3one line summary

A layered Mixture-of-Agents system combining multiple LLMs achieves state-of-the-art results on AlpacaEval 2.0 (65.1%), MT-Bench, and FLASK, outperforming GPT-4 Omni.

References

27 extracted · 27 resolved · 15 Pith anchors

[1] Qwen Technical Report · arXiv:2309.16609

[2] D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al 1901

[3] ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate · arXiv:2308.07201

[4] Reconcile: Round-table conference improves reasoning via consensus among diverse llms

[5] Active prompting with chain-of-thought for large language models

Formal links

3 machine-checked theorem links

Cited by

19 papers in Pith

TRINITY: An Evolved LLM Coordinator

SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6G

Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation

Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus

Receipt and verification

First computed	2026-05-17T23:38:46.841917Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

29046846fe88c12eef43e2e41079ccaa53c0884ccba9b9fb88fb5c6d1e796d15

Aliases

arxiv: 2406.04692 · arxiv_version: 2406.04692v1 · doi: 10.48550/arxiv.2406.04692 · pith_short_12: FECGQRX6RDAS · pith_short_16: FECGQRX6RDAS532D · pith_short_8: FECGQRX6

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/FECGQRX6RDAS532D4LSBA6OMVJ \
  | 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: 29046846fe88c12eef43e2e41079ccaa53c0884ccba9b9fb88fb5c6d1e796d15

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6100c257d76c8a53e9e86512a1e9e0ee9b8ac073424fc1f3ba63b79b9d39ce1e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-06-07T07:04:10Z",
    "title_canon_sha256": "3eca579e8e4dad3dfa8d40b5946b086c28c9157866b150f939aa4112d48a229b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2406.04692",
    "kind": "arxiv",
    "version": 1
  }
}