Pith Number

pith:SZI5HFTU

pith:2026:SZI5HFTUUZFFVISOAXCQ7F34WG

not attested not anchored not stored refs resolved

FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

Fengyi Wu, Hao Chen, Junzhe Yu, Kit Long Hon, Peng Chen, Yunlong Lyu

A multi-agent system automates the full library fuzzing lifecycle by evolving harnesses from runtime feedback.

arxiv:2605.14431 v1 · 2026-05-14 · cs.SE · cs.CR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SZI5HFTUUZFFVISOAXCQ7F34WG}

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

FuzzAgent completes the full fuzzing lifecycle for all 20 libraries without human intervention and reaches 179619 branches, exceeding OSS-Fuzz, PromptFuzz, PromeFuzz, and OSS-Fuzz-Gen by 45.1%, 73.2%, 92.1%, and 191.2%, respectively. FuzzAgent also identifies 102 genuine library bugs, 78 of which have already been acknowledged and fixed by upstream maintainers.

C2weakest assumption

That the multi-agent loop can reliably distinguish genuine library bugs from harness-induced crashes and that the runtime feedback signals are sufficient to drive meaningful iterative improvement without human oversight or post-hoc filtering.

C3one line summary

FuzzAgent deploys specialized agents that collaborate on harness generation, execution, and crash triage to evolve fuzzing campaigns, delivering 45-191% more branch coverage than four baselines on 20 C/C++ libraries and surfacing 102 real bugs.

References

109 extracted · 109 resolved · 4 Pith anchors

[1] The art, science, and engineering of fuzzing: A survey, 2021

[2] Fuzzers for stateful systems: Survey and research directions, 2024 · doi:10.1145/3648468

[3] Fuzzing vulnerability discovery techniques: Survey, challenges and future directions, 2022

[4] A survey of fuzzing open-source operating systems, 2025

[5] M. Zalewski, “American fuzzy lop,” http://lcamtuf.coredump.cx/afl/, Accessed 2026 2026

Receipt and verification

First computed	2026-05-17T23:39:07.132019Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9651d39674a64a5aa24e05c50f977cb19ec422150c73a78517125f9231d1ca4f

Aliases

arxiv: 2605.14431 · arxiv_version: 2605.14431v1 · doi: 10.48550/arxiv.2605.14431 · pith_short_12: SZI5HFTUUZFF · pith_short_16: SZI5HFTUUZFFVISO · pith_short_8: SZI5HFTU

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/SZI5HFTUUZFFVISOAXCQ7F34WG \
  | 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: 9651d39674a64a5aa24e05c50f977cb19ec422150c73a78517125f9231d1ca4f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7ed1c52e6482e8afdbfab9f7d48a0e24b73febe9719fcf8404921ec9c0b9c633",
    "cross_cats_sorted": [
      "cs.CR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-14T06:21:33Z",
    "title_canon_sha256": "9842339855befa574a7ca519d0d9cd5dc42c7b76fed32777468c14ab61665b29"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14431",
    "kind": "arxiv",
    "version": 1
  }
}