FirsthandTech
arXiv: cs.AI preprintsInternational20 November 2026

Who Is Behind the Harness? Verifying Model Identity in Coding Agents through Behavioral Fingerprinting

This is an official announcement record

Firsthand records what arXiv: cs.AI preprints announced and links to the original. The wording below is theirs, not ours.

arXiv:2609.28559v2 Announce Type: replace-cross Abstract: 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 Ident
Source: arXiv: cs.AI preprints

More from arXiv: cs.AI preprints

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.