AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks

arXiv:2609.37310 · cs.CR, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/karpathy/autoresearch

Terminology

• Robustness — 65× in this paper · explained in 5 episodes
• Verification — 35× in this paper · explained in 2 episodes
• Copula — 19× in this paper · explained in 2 episodes
• Large Language Model — 10× in this paper
• Core — 9× in this paper · explained in 2 episodes
• Clustering — 7× in this paper · explained in 2 episodes
• Perplexity — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Filler Tokens — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Anchor Tokens — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• A Watermark for Black-Box Language Models
• A Unified Framework for LLM Watermarks
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
• Discovering Preference Optimization Algorithms with and for Large Language Models
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
• ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs