Pith Number

pith:2PUHZY6N

pith:2026:2PUHZY6NP4F22ZWHTP3P4ZP6RY

not attested not anchored not stored refs resolved

LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning

Hua Wei, Kaize Ding, Xudong Chen, Yixin Liu

Training via localized counterfactual edits allows an LLM to generate executable multi-agent orchestrations that outperform prior methods on reasoning and coding benchmarks.

arxiv:2605.14483 v1 · 2026-05-14 · 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{2PUHZY6NP4F22ZWHTP3P4ZP6RY}

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

LEMON achieves state-of-the-art performance among the evaluated multi-agent orchestration methods on six reasoning and coding benchmarks including MMLU, GSM8K, AQuA, MultiArith, SVAMP, and HumanEval.

C2weakest assumption

That editing single orchestration fields and measuring the resulting reward contrast supplies reliable, localized credit assignment superior to standard execution-level feedback.

C3one line summary

LEMON trains an LLM orchestrator with counterfactual-augmented GRPO to produce deployable multi-agent specifications that reach state-of-the-art results on six reasoning and coding benchmarks.

References

35 extracted · 35 resolved · 8 Pith anchors

[1] Autogen: Enabling next-gen llm applications via multi-agent conversations 2024

[2] Camel: Communicative agents for" mind" exploration of large language model society.Advances in neural information processing systems, 36:51991–52008 2023

[3] Metagpt: Meta programming for a multi-agent collaborative framework 2023

[4] Large Language Model based Multi-Agents: A Survey of Progress and Challenges 2024 · arXiv:2402.01680

[5] Improv- ing factuality and reasoning in language models through multiagent debate 2024

Receipt and verification

First computed	2026-05-17T23:39:06.525807Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d3e87ce3cd7f0bad66c79bf6fe65fe8e3a22fa6f9717bbd618046fcf5f8ff633

Aliases

arxiv: 2605.14483 · arxiv_version: 2605.14483v1 · doi: 10.48550/arxiv.2605.14483 · pith_short_12: 2PUHZY6NP4F2 · pith_short_16: 2PUHZY6NP4F22ZWH · pith_short_8: 2PUHZY6N

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/2PUHZY6NP4F22ZWHTP3P4ZP6RY \
  | 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: d3e87ce3cd7f0bad66c79bf6fe65fe8e3a22fa6f9717bbd618046fcf5f8ff633

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "236757d0ccb35a66f11aa890ef56facf0f58ebbd3968e1fd69fee72bd6ec8a80",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T07:24:09Z",
    "title_canon_sha256": "4e19252c61acca31c7e638280dea611978d7de2676970ccf31a539c3e48334e0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14483",
    "kind": "arxiv",
    "version": 1
  }
}