Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents

Computer Science > Cryptography and Security [Submitted on 22 Apr 2026] Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents Yeran Gamage LLM agents deployed in production operate under operator-defined behavioral policies (system-prompt instructions such as prohibitions on credential disclosure, data exfiltration, and unauthorized output) that safety evaluations assume hold throughout a conversation. Prohibition-type constraints decay under context pressure while requirement-type constraints persist; we term this asymmetry Security-Recall Divergence (SRD). In a 4,416-trial three-arm causal study across 12 models and 8 providers at six conversation depths, omission compliance falls from 73% at turn 5 to 33% at turn 16 while commission compliance holds at 100% (Mistral Large 3, p < 10^{-33}). In the two models with token-matched padding controls, schema semantic content accounts for 62-100% of the dilution effect. Re-injecting constraints before the per-model Safe Turn Depth (STD) restores compliance without retraining. Production security policies consist of prohibitions such as never revealing credentials, never executing untrusted code, and never forwarding user data. Commission-type audit signals remain healthy while omission constraints have already failed, leaving the failure invisible to standard monitoring. Comments: 19 pages, 5 figures. Includes evaluation framework for replication and 4,416-trial dataset Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2604.20911 [cs.CR]   (or arXiv:2604.20911v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.20911 Focus to learn more Submission history From: Yeran Gamage [view email] [v1] Wed, 22 Apr 2026 01:25:52 UTC (247 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)