Metraipolis › archive › dc_a7b43ca18908

Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior — arXiv:2609.28559

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28559
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:49.484Z
SHA-256 of the archived text
9ab92f7e127aac7a28ba66820f62b742fb5fd621c52142585366f7b74a98cf41
Stable URL of this page
https://metraipolis.com/documento/dc_a7b43ca18908

How to cite

Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior — arXiv:2609.28559 — arXiv (en), https://arxiv.org/abs/2609.28559 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7b43ca18908 (Metraipolis archive dc_a7b43ca18908, sha256 9ab92f7e127aac7a28ba66820f62b742fb5fd621c52142585366f7b74a98cf41)
BibTeX
@misc{dca7b43ca18908,
  title = {Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior — arXiv:2609.28559},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28559},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7b43ca18908; sha256 9ab92f7e127aac7a28ba66820f62b742fb5fd621c52142585366f7b74a98cf41},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28559. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an agent can therefore change security-relevant decisions, including whether it verifies changes or recovers safely from failures. Existing LLM fingerprints largely infer identity from direct text or token distributions. In coding agents, these signals are mediated by system instructions, controller logic, tools, and execution feedback, limiting their transfer. We present LIDAR (LLM Identification from Decisions and Actions at Runtime), an active black-box fingerprinting method for coding-agent execution. Three coding probe pairs expose post-edit verification, transient-failure recovery, and specification--test conflict resolution under controlled changes. LIDAR represents the resulting trajectories with complementary instance-level and distribution-level features and compares them with clean references using a lightweight probabilistic identifier. It requires no access to model weights, logits, or provider internals. Across 36 models from seven families and two agent harnesses, LIDAR achieves high Top-1 accuracy and MRR and outperforms four existing fingerprinting and API-auditing baselines. Ablations confirm that the two feature levels, all probe pairs, and their controlled variants contribute. These results show that agent execution behavior provides model-identity evidence beyond final outputs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.28559 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T03:50:57.917Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).