Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

--> Computer Science > Artificial Intelligence arXiv:2606.07808 (cs) [Submitted on 5 Jun 2026] Title: Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models Authors: Sanjay Kariyappa , G. Edward Suh View a PDF of the paper titled Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models, by Sanjay Kariyappa and 1 other authors View PDF HTML (experimental) Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-privilege applicable instruction. Existing benchmarks largely measure this behavior end-to-end, asking whether the final response is compliant. However, a non-compliant response can arise from several distinct failures: the model may fail to identify the relevant instructions in context, fail to resolve conflicts among identified instructions, or correctly resolve the conflict in its reasoning while still producing a violating response. We introduce a white-box diagnostic framework that localizes instruction hierarchy failures into instruction identification, conflict resolution, and response realization, making failures more interpretable. We evaluate three reasoning models--Gemma-4-31B-IT, Qwen3.6-35B-A3B, and Claude Sonnet 4.6--on long-context adaptations of IHEval and IHChallenge, and find that the dominant failure mode varies across models, tasks, and context length. Building on the observation that models can often detect conflicts and output violations when explicitly prompted, we propose two training-free self-monitoring mechanisms: a parallel input monitor for low-latency conflict detection before generation, and a sequential output monitor for response-level review and repair. Across Gemma-4-31B-IT, Claude Sonnet 4.6, and GPT-5.3, the strongest monitor reduces rule-following non-compliance by 81-99%, with GPT-5.3 reductions of 86% under static attacks and 45% under adaptive attacks. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.07808 [cs.AI] (or arXiv:2606.07808v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2606.07808 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Sanjay Kariyappa [ view email ] [v1] Fri, 5 Jun 2026 19:36:48 UTC (502 KB) Full-text links: Access Paper: View a PDF of the paper titled Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models, by Sanjay Kariyappa and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? )