Pith Number

pith:LQDC6B5K

pith:2026:LQDC6B5K2WAFCMS55UKHM4V7NE

not attested not anchored not stored refs resolved

GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration

Md Rahmat Ullah, Musa Molla, Shafiq Joty, Yeahia Sarker

GraphBit defines LLM agent workflows as explicit DAGs executed by a Rust engine to eliminate routing hallucinations and improve reproducibility.

arxiv:2605.13848 v1 · 2026-03-08 · cs.AI · cs.CL · cs.DC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LQDC6B5K2WAFCMS55UKHM4V7NE}

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

Across GAIA benchmark tasks spanning zero-tool, document-augmented, and web-enabled workflows, GraphBit outperforms six existing frameworks, achieving the highest accuracy (67.6 percent), zero framework-induced hallucinations, the lowest latency (11.9 ms overhead), and the highest throughput.

C2weakest assumption

The assumption that explicit DAG orchestration with typed functions and a Rust engine can capture the necessary flexibility for diverse real-world workflows without the adaptability of prompted routing.

C3one line summary

GraphBit is a DAG-based engine-orchestrated framework for agentic LLMs that achieves 67.6% accuracy with zero hallucinations on GAIA benchmarks.

References

46 extracted · 46 resolved · 9 Pith anchors

[1] Large Language Model Agents: A Comprehensive Survey on Architectures, Capabilities, and Applications , author=. 2025 , publisher= 2025

[2] Junwei Yu and Yepeng Ding and Hiroyuki Sato , year=

[3] A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems , author=. 2025 , eprint= 2025

[4] LLM-based agentic reasoning frameworks: A survey from methods to scenarios

[5] The Twelfth International Conference on Learning Representations , year=

Receipt and verification

First computed	2026-05-17T23:39:19.639271Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5c062f07aad58051325ded147672bf692d4eb39a70b799e905b687f9fd565830

Aliases

arxiv: 2605.13848 · arxiv_version: 2605.13848v1 · doi: 10.48550/arxiv.2605.13848 · pith_short_12: LQDC6B5K2WAF · pith_short_16: LQDC6B5K2WAFCMS5 · pith_short_8: LQDC6B5K

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/LQDC6B5K2WAFCMS55UKHM4V7NE \
  | 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: 5c062f07aad58051325ded147672bf692d4eb39a70b799e905b687f9fd565830

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "de6faca86a82e5e0d336bab6e0d75086120a1e7481da4bf8e2edcafd457de10f",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.DC"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-03-08T18:32:28Z",
    "title_canon_sha256": "dbdfafcff0144142c5f24f139f16e0286100e254a3a30628b16251af463927a4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13848",
    "kind": "arxiv",
    "version": 1
  }
}