arXiv:2606. 08932v1 Announce Type: cross Abstract: Rule-following agents tasked with executing policies and regulations often fail via Silent Scope Omission (SSO): a model applies a general rule but silently drops nested exceptions or counter-exceptions, producing outputs that appear compliant yet break on important edge cases.
arXiv:2607. 23386v1 Announce Type: new Abstract: We document a failure class in frontier large language models -- exception chain collapse -- observed in eligibility evaluation under nested conditional rules of the form "A is required UNLESS B applies, UNLESS C overrides B".
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
The paper introduces the concept of Compositional Policy Violations (CPVs), where each step in an agentic AI workflow passes its individual compliance check, yet the overall execution violates higher‑level policies such as referral thresholds or authority limits. It categorizes CPVs into four types—Authority Creep, Threshold Laundering, Cumulative Sum Violation, and Context Collapse—and argues that the appropriate remedy depends on where the guarded quantity changes. To address this, the authors propose a provenance‑aware runtime architecture that evaluates policies over complete execution traces, recomputing guarded quantities from raw provenance rather than relying on step‑level outputs.
arXiv:2607. 11951v1 Announce Type: new Abstract: Large language models can write SQL, but enterprise deployment demands more than plausible text: outputs must be syntactically valid, must respect per-role and per-schema policy, must carry provable (not best-effort) guarantees, must not slow down as generations grow, and must leave a compliance-grade record of every decision.
arXiv:2607. 18357v1 Announce Type: cross Abstract: Large language models now write a growing share of the world's code, increasingly inside agents and serving systems that compile, execute, or dispatch generated code without line-by-line review.
SemVerBench is a benchmark that evaluates how well large language models (LLMs) understand and apply version-constraint resolution semantics, such as determining whether a version satisfies constraints like ^1.2.3 or >=2.0. The study finds that many models struggle with certain corner cases, with GPT‑5.1 performing poorly while Claude and Opus perform much better. The authors suggest that the failures stem from an activation/application gap rather than a lack of knowledge, and recommend that coding agents delegate version resolution to a dedicated resolver tool.
arXiv:2608. 12426v1 Announce Type: new Abstract: Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries, output schemas.
arXiv:2604. 06173v2 Announce Type: replace-cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning.
arXiv:2608. 09028v1 Announce Type: new Abstract: Institutional policies stay in natural language while the systems that check compliance demand machine-readable constraints.
arXiv:2607. 13069v1 Announce Type: new Abstract: Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises.
arXiv:2608. 10137v1 Announce Type: cross Abstract: Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step.
The paper introduces Grounded Normative Rule Generation (GNRS) and a new framework called GNRS-Search that uses Markov Chain Monte Carlo sampling to optimize a discrete And-Or Graph for rule synthesis. By separating operational feasibility from prose generation, the method localizes rule failures before final text creation. Evaluations on GNRS-Bench and RealCharter-Bench show significant improvements in rubric quality and executable metrics, demonstrating that the gains come from robust operational logic rather than stylistic tuning.