pith. sign in
Pith Number

pith:TWC7UP34

pith:2026:TWC7UP34FNVON73AMMDYRTTUPB
not attested not anchored not stored refs resolved

Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights

Huan Wang, Jian Wang, Kai Wang, Wenrui Bao, Yuzhang Shang, Zhangyang Wang

Multi-agent LLMs can collaborate by mapping sender activations directly into transient low-rank weight updates on the receiver instead of passing text messages.

arxiv:2605.13839 v1 · 2026-05-13 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{TWC7UP34FNVON73AMMDYRTTUPB}

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

With three Qwen3-4B agents, TFlow improves over a standalone receiver by up to 8.5 accuracy points across five benchmarks while reducing processed tokens by up to 32.69%. Compared with a text-based three-agent baseline, it reduces total processed tokens by up to 83.27% and the wall-clock inference time by up to 4.6×, while maintaining competitive accuracy on four of five benchmarks.

C2weakest assumption

That a learned parameter generator, trained once, can map arbitrary sender activations into effective, stable, receiver-specific LoRA perturbations for every new query without overfitting or degrading generation quality.

C3one line summary

TFlow enables multi-agent LLMs to collaborate via transient low-rank LoRA perturbations derived from sender activations, yielding up to 8.5 accuracy gains and 83% token reduction versus text-based baselines on Qwen3-4B models.

References

58 extracted · 58 resolved · 11 Pith anchors

[1] Li, G., H. Hammoud, H. Itani, et al. Camel: Communicative agents for" mind" exploration of large language model society. InNeurIPS. 2023 2023
[2] Hong, S., M. Zhuge, J. Chen, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InICLR. 2023 2023
[3] Wu, Q., G. Bansal, J. Zhang, et al. AutoGen: Enabling next-gen LLM applications via multi- agent conversations. InCOLM. 2024 2024
[4] Du, Y ., S. Li, A. Torralba, et al. Improving factuality and reasoning in language models through multiagent debate. InICML. 2024 2024
[5] Liang, T., Z. He, W. Jiao, et al. Encouraging divergent thinking in large language models through multi-agent debate. InEMNLP. 2024 2024
Receipt and verification
First computed 2026-05-18T02:44:09.566975Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

9d85fa3f7c2b6ae6ff60630788ce74787c796f0d7b88a5e1978956ebbc177c1d

Aliases

arxiv: 2605.13839 · arxiv_version: 2605.13839v1 · doi: 10.48550/arxiv.2605.13839 · pith_short_12: TWC7UP34FNVO · pith_short_16: TWC7UP34FNVON73A · pith_short_8: TWC7UP34
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/TWC7UP34FNVON73AMMDYRTTUPB \
  | 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: 9d85fa3f7c2b6ae6ff60630788ce74787c796f0d7b88a5e1978956ebbc177c1d
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "2e823e305e915b0bf42db7b3bc647741a3e8de05c623468c4f13b128f471c999",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T17:58:32Z",
    "title_canon_sha256": "0c3d912d52ea26cf8cfbc5482f2cc7d0cb63bfe9edd78b5532797e889e5f7692"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13839",
    "kind": "arxiv",
    "version": 1
  }
}