# ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning

arXiv: https://arxiv.org/abs/2510.15211 · HTML: https://mlsanity.com/paper/2510.15211/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 24 of 24)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2504.01296/) (2025)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability](https://mlsanity.com/paper/2402.18667/) (2024)
- [Self-Reflection in LLM Agents: Effects on Problem-Solving Performance](https://mlsanity.com/paper/2405.06682/) (2024)
- [Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models](https://mlsanity.com/paper/2505.14810/) (2025)
- [Do LLMs "know" internally when they follow instructions?](https://mlsanity.com/paper/2410.14516/) (2024)
- [Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering](https://mlsanity.com/paper/2505.12025/) (2025)
- [M-IFEval: Multilingual Instruction-Following Evaluation](https://mlsanity.com/paper/2502.04688/) (2025)
- [IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval](https://mlsanity.com/paper/2503.04644/) (2025)
- [CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models](https://mlsanity.com/paper/2402.13109/) (2024)
- [EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models](https://mlsanity.com/paper/2506.08375/) (2025)
- [Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuning](https://mlsanity.com/paper/2505.11922/) (2025)

## Built on by (most cited first, 13 of 13)

- [Reasoning Models Struggle to Control their Chains of Thought](https://mlsanity.com/paper/2603.05706/) (2026)
- [Automated Benchmark Auditing for AI Agents and Large Language Models](https://mlsanity.com/paper/2605.26079/) (2026)
- [Reasoning Models Will Sometimes Lie About Their Reasoning](https://mlsanity.com/paper/2601.07663/) (2026)
- [PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations](https://mlsanity.com/paper/2604.16909/) (2026)
- [Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents](https://mlsanity.com/paper/2606.22953/) (2026)
- [K2-V2: A 360-Open, Reasoning-Enhanced LLM](https://mlsanity.com/paper/2512.06201/) (2025)
- [FLEx: Language Modeling with Few-shot Language Explanations](https://mlsanity.com/paper/2601.04157/) (2026)
- [Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models](https://mlsanity.com/paper/2604.13706/) (2026)
- [Verifier-Induced Support Reshaping in On-Policy Optimization](https://mlsanity.com/paper/2608.00220/) (2026)
- [Brain-LLM Alignment Tracks Training Data, Not Typology](https://mlsanity.com/paper/2605.23032/) (2026)
- [When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following](https://mlsanity.com/paper/2606.09662/) (2026)
- [Can Reasoning Models Detect Changes to their Chains of Thought?](https://mlsanity.com/paper/2606.22085/) (2026)
- [Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops](https://mlsanity.com/paper/2610.15738/) (2026)

## Abstract (arXiv)

The ability of large language models (LLMs) to follow user instructions is central to their reliability, safety, and usefulness. While prior studies assess instruction adherence in the model's main responses, we argue that it is also critical for large reasoning models (LRMs) to follow user instructions throughout their reasoning process. Reasoning instruction following makes LRMs more controllable and transparent, while reducing risks of undesirable shortcuts, hallucinations, or reward hacking within reasoning traces. To evaluate this dimension, we introduce ReasonIF, a systematic benchmark for assessing reasoning instruction following. ReasonIF includes six categories of instruction prompts, spanning multilingual reasoning, formatting and length control. Across many open-source LRMs including GPT-OSS, Qwen3, and DeepSeek-R1, we find substantial failures in reasoning instruction adherence: the highest instruction following score (IFS) remains below 0.25, meaning that fewer than 25% of reasoning traces comply with the given instructions. Notably, as task difficulty increases, reasoning instruction following degrades further. We also explore two strategies to enhance reasoning instruction fidelity. (1) multi-turn reasoning and (2) Reasoning Instruction Finetuning (RIF) using synthetic data. RIF improves the IFS of GPT-OSS-20B from 0.11 to 0.27, indicating measurable progress but leaving ample room for improvement.