# WIRE: Profiling Witnessed Within-Policy Instruction Collisions in LLM Agents

arXiv: https://arxiv.org/abs/2605.27784 · HTML: https://mlsanity.com/paper/2605.27784/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 15 of 15)

- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [Task-Oriented Dialogue as Dataflow Synthesis](https://mlsanity.com/paper/2009.11423/) (2020)
- [SatLM: Satisfiability-Aided Language Models Using Declarative Prompting](https://mlsanity.com/paper/2305.09656/) (2023)
- [Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?](https://mlsanity.com/paper/2403.06833/) (2024)
- [Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?](https://mlsanity.com/paper/2310.01831/) (2023)
- [Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments](https://mlsanity.com/paper/2302.11649/) (2023)
- [IHEval: Evaluating Language Models on Following the Instruction Hierarchy](https://mlsanity.com/paper/2502.08745/) (2025)
- [A Closer Look at System Prompt Robustness](https://mlsanity.com/paper/2502.12197/) (2025)
- [Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands](https://mlsanity.com/paper/1904.09020/) (2019)
- [ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions](https://mlsanity.com/paper/2511.14342/) (2025)
- [ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialogues](https://mlsanity.com/paper/2203.12751/) (2022)
- [Arbiter: Detecting Interference in LLM Agent System Prompts](https://mlsanity.com/paper/2603.08993/) (2026)

## Abstract (arXiv)

LLM agents are governed by long-lived prompt policies, where individually reasonable stand- ing rules can jointly govern the same pre- generation state. Existing instruction-following evaluations usually ask whether a model satis- fies explicit constraints, but they do not show how a model resolves pressure among rules inside one standing policy. We introduce WIRE, a witnessed resolu- tion profiler for prompt policies. WIRE ex- tracts source-grounded rules, encodes them as PYRULE clauses, uses satisfiability checks only to nominate same-surface hard-collision can- didates, realizes those candidates as concrete co-governance witnesses, and executes subject models to produce a four-cell resolution profile: satisfy both rules, only the earlier rule, only the later rule, or neither. Across six public prompt policies, WIRE ex- tracts 276 source rules and 560 clauses, clas- sifies 30,944 within-policy clause-pair com- parisons, retains 170 encoded hard-collision source-rule pairs, and realizes 1,402 concrete witnesses. In policy-only evaluation, these wit- nesses yield 13,335 jointly governed, judgeable trials; only 35.4% satisfy both governed rules. The resulting profiles reveal policy-specific, model-specific, and tool-interface-specific res- olution patterns. WIRE is not a proof of natural-language contra- diction, a deployment-frequency estimator, or a root-cause diagnosis. It is a measurement tool that returns reproducible witnesses and aggre- gate profiles for inspection, regression testing, and repair.